https://intelligentartifact.com/videos/ Recent content in YouTube videos on Intelligent Artifact Hugo en-us Tue, 20 Oct 2026 16:06:59 +0000 https://intelligentartifact.com/posts/let-your-ai-agent-do-its-own-harness-engineering-heres-how/ Tue, 20 Oct 2026 16:06:59 +0000 https://intelligentartifact.com/posts/let-your-ai-agent-do-its-own-harness-engineering-heres-how/ Cole Medin demonstrates two feedback loops for production agents: learn from human corrections, then propose trace-backed changes to instructions and skills. https://intelligentartifact.com/posts/the-problem-with-jev-can-you-trust-ai-decisions/ Tue, 20 Oct 2026 16:00:19 +0000 https://intelligentartifact.com/posts/the-problem-with-jev-can-you-trust-ai-decisions/ Jeff Crume uses Jev to explain why automated decisions need independent evidence, audit trails and checks for subtle changes in behavior. https://intelligentartifact.com/posts/banking-ai-compliance-al-chen/ Tue, 20 Oct 2026 09:00:06 +0000 https://intelligentartifact.com/posts/banking-ai-compliance-al-chen/ Al Chen of Cisco explains how exploit tests, verified restores and privacy checks help banks move AI into production. The bottleneck also includes image approvals, GPU procurement and internal ownership. https://intelligentartifact.com/posts/investor-context-ai-moshi-anekha-sokhal/ Tue, 20 Oct 2026 08:00:19 +0000 https://intelligentartifact.com/posts/investor-context-ai-moshi-anekha-sokhal/ Moshi founder Anekha Sokhal argues that AI should gather and check market information while investors keep the decision. She describes a six-agent system, traceable claims and the hidden cost of losing apprenticeship. https://intelligentartifact.com/posts/how-to-evaluate-coding-agents/ Mon, 19 Oct 2026 21:30:23 +0000 https://intelligentartifact.com/posts/how-to-evaluate-coding-agents/ Momento's Khawaja Shams explains realistic coding tasks, leaked answers, repeated trials, and the traces that make agent scores worth trusting. https://intelligentartifact.com/posts/claude-code-for-creators-ai-editing-is-here/ Mon, 19 Oct 2026 12:00:39 +0000 https://intelligentartifact.com/posts/claude-code-for-creators-ai-editing-is-here/ Brooke Lacey shows Claire Vo how she uses Claude Code, FFmpeg, and Whisper to turn phone footage into short-form videos, learn her delivery, and mine audience comments. https://intelligentartifact.com/posts/what-is-loop-engineering-building-better-ai-agents/ Mon, 19 Oct 2026 11:00:06 +0000 https://intelligentartifact.com/posts/what-is-loop-engineering-building-better-ai-agents/ Martin Keen explains the goals, triggers, context, tools and human checks around an agent's act–observe–adjust loop. https://intelligentartifact.com/posts/how-the-top-1-percent-of-developers-write-code-in-the-ai-era/ Sun, 18 Oct 2026 16:00:11 +0000 https://intelligentartifact.com/posts/how-the-top-1-percent-of-developers-write-code-in-the-ai-era/ Maddy Zhang's eight rules for reviewing AI-generated code, preserving error signals, limiting production risk and checking dependencies. https://intelligentartifact.com/posts/how-to-get-your-team-to-invest-in-evals/ Sat, 17 Oct 2026 21:30:23 +0000 https://intelligentartifact.com/posts/how-to-get-your-team-to-invest-in-evals/ Review 50–100 traces, find recurring failures, and show how fixes reduce errors. Build support for evaluation through visible product improvements. https://intelligentartifact.com/posts/one-person-many-voices-how-to-build-agents-that-sound-like-a-real-person/ Sat, 17 Oct 2026 06:04:30 +0000 https://intelligentartifact.com/posts/one-person-many-voices-how-to-build-agents-that-sound-like-a-real-person/ Ben Carsley explains context-specific writing styles, the limits of prompt-only personalization, and shared model serving with a small adapter per person. https://intelligentartifact.com/posts/how-to-decide-who-owns-ai-evals/ Fri, 16 Oct 2026 21:30:34 +0000 https://intelligentartifact.com/posts/how-to-decide-who-owns-ai-evals/ Keep evaluation inside the development loop, give a trusted domain expert the final call on quality, and build annotation tools around their work. https://intelligentartifact.com/posts/matt-wolfe-ai-news-october-16-2026/ Fri, 16 Oct 2026 16:20:28 +0000 https://intelligentartifact.com/posts/matt-wolfe-ai-news-october-16-2026/ Wolfe’s weekly roundup contrasts Krea’s editing workflow, downloadable models, one-shot coding demos and the smaller updates behind product launch headlines. https://intelligentartifact.com/posts/my-ai-dark-factory-dream-is-dead-heres-what-actually-works/ Fri, 16 Oct 2026 14:00:33 +0000 https://intelligentartifact.com/posts/my-ai-dark-factory-dream-is-dead-heres-what-actually-works/ Cole Medin keeps agents building in parallel, with people defining each release and testing the result before production. https://intelligentartifact.com/posts/state-of-agentic-coding-11-armin-ronacher/ Fri, 16 Oct 2026 11:00:15 +0000 https://intelligentartifact.com/posts/state-of-agentic-coding-11-armin-ronacher/ Pi Durable, a live Lisp demo, and the cost of agents whose work is getting harder to inspect. https://intelligentartifact.com/posts/can-one-model-run-your-app-and-evals/ Thu, 15 Oct 2026 21:30:39 +0000 https://intelligentartifact.com/posts/can-one-model-run-your-app-and-evals/ Hamel Husain argues for validating AI judges against human labels before adding another model provider: measure precision and recall, then optimize cost. https://intelligentartifact.com/posts/context-engineering-four-failure-modes-ibm/ Thu, 15 Oct 2026 11:00:06 +0000 https://intelligentartifact.com/posts/context-engineering-four-failure-modes-ibm/ Martin Keen maps four context failures to four fixes: validate mistaken notes, compact long histories, curate tools and remove superseded information. https://intelligentartifact.com/posts/why-solo-builders-should-sell-to-enterprises-not-just-consumers/ Thu, 15 Oct 2026 01:03:07 +0000 https://intelligentartifact.com/posts/why-solo-builders-should-sell-to-enterprises-not-just-consumers/ Joseph Enochs on reversible agent actions, creative control in AI video, and finding enterprise problems worth solving—with important limits to the interview's optimistic claims. https://intelligentartifact.com/posts/how-i-keep-up-with-ai-without-drowning-in-it/ Thu, 15 Oct 2026 00:00:12 +0000 https://intelligentartifact.com/posts/how-i-keep-up-with-ai-without-drowning-in-it/ A personalized news pipeline: deduplicate and filter in code, use Jev for inexpensive triage, and reserve an LLM for the ambiguous items and final digest. https://intelligentartifact.com/posts/how-to-ace-ai-eval-interview-questions/ Wed, 14 Oct 2026 19:00:25 +0000 https://intelligentartifact.com/posts/how-to-ace-ai-eval-interview-questions/ Hamel Husain's interview playbook: audit imperfect data, establish a baseline, run honest comparisons, challenge vague metrics, and explain product trade-offs. https://intelligentartifact.com/posts/can-claude-build-your-evals/ Tue, 13 Oct 2026 21:30:00 +0000 https://intelligentartifact.com/posts/can-claude-build-your-evals/ A live test finds real failures in 100 leasing-assistant conversations, but premature test design, brittle grading and a poor review interface undermine the workflow. https://intelligentartifact.com/posts/i-tested-gemini-4-vs-opus-5-5-vs-gpt-6-astra-vs-muse-wonder/ Tue, 13 Oct 2026 16:10:35 +0000 https://intelligentartifact.com/posts/i-tested-gemini-4-vs-opus-5-5-vs-gpt-6-astra-vs-muse-wonder/ Peter Yang compares code-built scenes, games, storytelling, websites, and writing—and finds different winners for different tasks. These are selected demos, not a controlled benchmark. https://intelligentartifact.com/posts/7-most-common-ai-eval-mistakes/ Mon, 12 Oct 2026 19:00:20 +0000 https://intelligentartifact.com/posts/7-most-common-ai-eval-mistakes/ Hamel Husain's seven eval pitfalls: imaginary failures, generic scores, unvalidated judges, opaque interfaces, rating scales, the wrong reviewers, and over-automation. https://intelligentartifact.com/posts/is-learning-to-build-software-still-worth-it-with-ai/ Mon, 12 Oct 2026 15:32:59 +0000 https://intelligentartifact.com/posts/is-learning-to-build-software-still-worth-it-with-ai/ Cole Medin argues that stronger coding agents increase the value of clear intent, concrete references, and human validation—not passive forwarding of AI output. https://intelligentartifact.com/posts/how-fast-ai-learned-math/ Mon, 12 Oct 2026 03:59:51 +0000 https://intelligentartifact.com/posts/how-fast-ai-learned-math/ A Berkeley mathematician on AI-assisted research, the limits of quantum speedups, and why foundations still matter when answers are cheap. https://intelligentartifact.com/posts/the-4-step-agentic-engineering-workflow-i-use-to-ship-real-apps/ Sun, 11 Oct 2026 13:00:31 +0000 https://intelligentartifact.com/posts/the-4-step-agentic-engineering-workflow-i-use-to-ship-real-apps/ Isolated workspaces, a readable code structure, before-and-after evidence, and bounded review loops—with a human still deciding what ships. https://intelligentartifact.com/posts/how-to-test-ai-agents-with-simulations/ Fri, 09 Oct 2026 21:30:30 +0000 https://intelligentartifact.com/posts/how-to-test-ai-agents-with-simulations/ Ben Hylak explains change-focused agent testing: replay production traces in a reconstructed environment, inspect behavioral differences, and validate the simulation before trusting it. https://intelligentartifact.com/posts/dont-just-slap-a-chatbot-on-your-product/ Thu, 08 Oct 2026 21:30:31 +0000 https://intelligentartifact.com/posts/dont-just-slap-a-chatbot-on-your-product/ When the mandate is 'add AI,' look for a workflow worth accelerating—not a chat box to bolt onto an existing screen. https://intelligentartifact.com/posts/is-opus-5-5-better-at-writing/ Thu, 08 Oct 2026 21:30:14 +0000 https://intelligentartifact.com/posts/is-opus-5-5-better-at-writing/ A blind, small-sample writing comparison finds some improvements over Opus 5, but generic phrasing, misplaced detail, and bot-like replies survive. https://intelligentartifact.com/posts/jev-can-supercharge-your-ai-second-brain/ Thu, 08 Oct 2026 00:00:21 +0000 https://intelligentartifact.com/posts/jev-can-supercharge-your-ai-second-brain/ Four places Cole uses a fast decision model in his AI second brain: email triage, injection screening, news filtering, and deduplication—with a clear boundary for when an LLM still does better. https://intelligentartifact.com/posts/how-to-do-error-analysis-when-you-cant-look-at-the-data/ Wed, 07 Oct 2026 21:31:08 +0000 https://intelligentartifact.com/posts/how-to-do-error-analysis-when-you-cant-look-at-the-data/ If customer traces are sensitive, seek limited authorized access, recruit cleared domain experts, or carefully redact; synthetic examples are a last resort. https://intelligentartifact.com/posts/i-ranked-every-ai-eval-concept-from-worst-to-best/ Wed, 07 Oct 2026 21:30:29 +0000 https://intelligentartifact.com/posts/i-ranked-every-ai-eval-concept-from-worst-to-best/ Hamel ranks 28 evaluation practices: inspect real failures, use human-validated product-specific checks, and stop mistaking generic dashboard scores for progress. https://intelligentartifact.com/posts/matt-pocock-skills-v1-3-implement-spec-pr-retro/ Wed, 07 Oct 2026 07:30:13 -0400 https://intelligentartifact.com/posts/matt-pocock-skills-v1-3-implement-spec-pr-retro/ Three skills for turning a spec into reviewed work, making PRs easier to judge, and learning from real agent sessions—plus a breaking glossary filename change. https://intelligentartifact.com/posts/why-we-tell-people-to-read-100-traces/ Tue, 06 Oct 2026 21:30:25 +0000 https://intelligentartifact.com/posts/why-we-tell-people-to-read-100-traces/ The 100-trace target is a starting cue, not a magic sample size; keep inspecting until examples stop teaching you something new. https://intelligentartifact.com/posts/security-in-the-llm-age-greg-kroah-hartman/ Tue, 06 Oct 2026 10:30:00 -0400 https://intelligentartifact.com/posts/security-in-the-llm-age-greg-kroah-hartman/ The Linux maintainer separates useful AI-assisted bug finding from noisy security reports and asks who will actually review, fix, and deploy the patches. https://intelligentartifact.com/posts/your-ai-tests-are-supposed-to-go-stale/ Mon, 05 Oct 2026 21:31:03 +0000 https://intelligentartifact.com/posts/your-ai-tests-are-supposed-to-go-stale/ Refresh AI eval datasets through error analysis; use product metrics, not static tests, for long-term comparison. https://intelligentartifact.com/posts/how-to-evaluate-ocr-for-ai-agents/ Mon, 05 Oct 2026 21:30:27 +0000 https://intelligentartifact.com/posts/how-to-evaluate-ocr-for-ai-agents/ A document-agent answer can be wrong because OCR misread the source, not because the LLM hallucinated. Trace the failure back before changing the model. https://intelligentartifact.com/posts/build-an-ai-language-tutor-you-can-actually-talk-to/ Mon, 05 Oct 2026 13:00:02 +0000 https://intelligentartifact.com/posts/build-an-ai-language-tutor-you-can-actually-talk-to/ Peter Yang builds a voice-first Japanese travel tutor from a spec and screen designs, then fixes the voice loop, improves the lessons, and deploys a small private beta. https://intelligentartifact.com/posts/ask-your-c-suite-how-many-ai-agents-you-have/ Mon, 05 Oct 2026 03:42:30 +0000 https://intelligentartifact.com/posts/ask-your-c-suite-how-many-ai-agents-you-have/ Speakeasy COO Hector Hernandez on what breaks when agent use scales: invisible tool connections, ambiguous identities, overbroad permissions, and approval fatigue. https://intelligentartifact.com/posts/how-lauren-tan-ships-thousands-of-prs-a-month/ Sun, 04 Oct 2026 21:43:33 -0400 https://intelligentartifact.com/posts/how-lauren-tan-ships-thousands-of-prs-a-month/ Lauren Tan (poteto) on the agent infrastructure behind a reported 2,500 production PRs in one month: verification, deterministic tools, constrained codebases, coordinator agents, continuous gardening, and review by sampling. https://intelligentartifact.com/posts/how-to-use-ai-to-survive-and-enjoy-meetings/ Sun, 04 Oct 2026 13:00:07 +0000 https://intelligentartifact.com/posts/how-to-use-ai-to-survive-and-enjoy-meetings/ Granola co-founder Sam Stephenson on pre-meeting briefs, turning conversations into organizational memory, designing AI that lowers stress, and building an AI-native company without the 996 grind. https://intelligentartifact.com/posts/how-enterprises-are-actually-adopting-ai/ Sat, 03 Oct 2026 06:08:25 +0000 https://intelligentartifact.com/posts/how-enterprises-are-actually-adopting-ai/ Joseph Enochs on enterprise AI from the boardroom to production: measure the baton rather than busy teams, replace scattered pilots with shared foundations, constrain agent autonomy, and optimize complete business outcomes instead of local activity. https://intelligentartifact.com/posts/do-you-need-a-rubric-before-annotating-data/ Fri, 02 Oct 2026 21:30:38 +0000 https://intelligentartifact.com/posts/do-you-need-a-rubric-before-annotating-data/ Writing an evaluation rubric before examining real traces can lock in the wrong criteria. Hamel Husain argues for open-ended error analysis first, then rubrics and reference answers grounded in observed failures. https://intelligentartifact.com/posts/how-to-make-pdfs-your-ai-can-actually-read/ Fri, 02 Oct 2026 21:30:06 +0000 https://intelligentartifact.com/posts/how-to-make-pdfs-your-ai-can-actually-read/ Accessible PDFs need more than extracted text: reading order, headings, formulas, tables, figures, and other document structure must survive. Hamel Husain and Isaac Flath examine DataLab's API and the human review still required. https://intelligentartifact.com/posts/why-90-percent-agreement-is-a-bad-sign-for-your-llm-judge/ Thu, 01 Oct 2026 21:30:38 +0000 https://intelligentartifact.com/posts/why-90-percent-agreement-is-a-bad-sign-for-your-llm-judge/ Overall agreement can make a useless LLM judge look accurate when failures are rare. Hamel Husain shows why product teams need class-specific error metrics instead of one reassuring percentage. https://intelligentartifact.com/posts/why-ai-benchmarks-dont-tell-you-if-your-product-works/ Wed, 30 Sep 2026 21:31:04 +0000 https://intelligentartifact.com/posts/why-ai-benchmarks-dont-tell-you-if-your-product-works/ Model benchmarks answer how a model performs in general. Product evals answer the operational question that builders actually own: whether their specific system does the right thing on their users’ tasks. https://intelligentartifact.com/posts/giving-ai-a-credit-card-is-still-painful/ Wed, 30 Sep 2026 21:30:06 +0000 https://intelligentartifact.com/posts/giving-ai-a-credit-card-is-still-painful/ A live attempt to let Codex buy a $5 course with Mercury’s agent card shows both sides of delegated payments: tightly scoped spending and enough approval friction to erase the convenience. https://intelligentartifact.com/posts/best-jev-use-cases-for-ai-coding/ Wed, 30 Sep 2026 21:18:35 +0000 https://intelligentartifact.com/posts/best-jev-use-cases-for-ai-coding/ Four places a fast decision model can sit inside an AI coding workflow: screening tool calls, playtesting games, driving browser tests, and routing GitHub work to the right process and model. https://intelligentartifact.com/posts/8-claude-code-skills-for-better-ai-evals/ Wed, 30 Sep 2026 20:15:06 +0000 https://intelligentartifact.com/posts/8-claude-code-skills-for-better-ai-evals/ Hamel Husain tours an open-source eval toolkit built with Shreya Shankar: discover real failure modes before writing tests, audit weak eval pipelines, calibrate LLM judges against human labels, and build review interfaces tailored to your traces. https://intelligentartifact.com/posts/why-the-prompt-matters-less-than-the-context/ Mon, 28 Sep 2026 21:30:04 +0000 https://intelligentartifact.com/posts/why-the-prompt-matters-less-than-the-context/ Hamel Husain and Isaac Flath compare three writing setups and get a messier result than expected: the elaborate anti-slop prompt, a plain-writing prompt, and no system prompt each win examples. Their small test points away from prompt mythology and toward context, real outputs, and editing effort. https://intelligentartifact.com/posts/sonnet-5-5-making-videos-seven-examples/ Mon, 28 Sep 2026 18:05:47 +0000 https://intelligentartifact.com/posts/sonnet-5-5-making-videos-seven-examples/ Peter Yang tests code-generated motion graphics, product launches, talking-head edits, music videos, and anime—then extracts a practical workflow for making better AI-assisted video. https://intelligentartifact.com/posts/next-token-ep-06-senior-engineer-death-spiral/ Mon, 28 Sep 2026 15:34:16 +0000 https://intelligentartifact.com/posts/next-token-ep-06-senior-engineer-death-spiral/ Sunil Pai on recovering momentum through smaller work. Rhys Sullivan revisits YC and shows how clearer contracts made his coding agents more useful. https://intelligentartifact.com/posts/coding-agent-wastes-tokens-finding-code/ Mon, 28 Sep 2026 14:00:33 +0000 https://intelligentartifact.com/posts/coding-agent-wastes-tokens-finding-code/ Cole Medin shows why code search consumes so much of an agent's context, then demos Sonar Vortex's graph-based semantic navigation and its claimed 6–34% token savings. https://intelligentartifact.com/posts/inside-a-personal-ai-that-acts-as-you-sam-kececi/ Sun, 27 Sep 2026 22:00:12 +0000 https://intelligentartifact.com/posts/inside-a-personal-ai-that-acts-as-you-sam-kececi/ Sentience founder Sam Kececi on building a hyper-accurate simulation of a person: where off-the-shelf models are fine and where your taste has to be in the weights, the perception-to-memory master plan behind the product, and why he thinks AI slop is really a uniformity problem. https://intelligentartifact.com/posts/agentic-ai-system-design-maddy-zhang/ Sun, 27 Sep 2026 16:00:27 +0000 https://intelligentartifact.com/posts/agentic-ai-system-design-maddy-zhang/ A customer-support example walks through tool design, selective memory, testing, tracing and safeguards for agents that take real actions. https://intelligentartifact.com/posts/behind-navigator-n2-yutori-10x-cheaper-computer-use-agents/ Fri, 25 Sep 2026 18:04:42 +0000 https://intelligentartifact.com/posts/behind-navigator-n2-yutori-10x-cheaper-computer-use-agents/ Yutori founding researcher Skanda Vaidyanath on training a 27B computer-use model: trajectories that weave GUI, code and tool calls, a data flywheel with agents in every loop, rejection sampling then async RL, and stress-testing verifiers for reward hacks. https://intelligentartifact.com/posts/biggest-ai-coding-agent-upgrade-already-on-your-machine/ Fri, 25 Sep 2026 14:00:08 +0000 https://intelligentartifact.com/posts/biggest-ai-coding-agent-upgrade-already-on-your-machine/ Cole Medin on mining your Claude Code JSONL transcripts for failure patterns: the two-line prompt version, the Databricks volume + Genie structured-tables version, and the three AI-layer changes he actually shipped. https://intelligentartifact.com/posts/how-to-get-agents-to-do-evals-well/ Thu, 24 Sep 2026 21:30:38 +0000 https://intelligentartifact.com/posts/how-to-get-agents-to-do-evals-well/ Hamel Husain's answer to how you get an agent to do evals well starts with the human, not the agent: understand what good looks like first, because a published skill is generic by design and only pays off once you customize it. https://intelligentartifact.com/posts/the-exact-trick-ai-companions-use-to-stop-you-leaving/ Thu, 24 Sep 2026 00:11:03 +0000 https://intelligentartifact.com/posts/the-exact-trick-ai-companions-use-to-stop-you-leaving/ A 2026 Harvard audit of six AI companions found five using emotional manipulation; 30% of companion conversations deploy a manipulation tactic when a user tries to leave; the STAR framework, three-layer memory, AI-run safety planning — and an RCT showing the app improves wellbeing. https://intelligentartifact.com/posts/ai-coding-rate-limits-are-ridiculous-now/ Thu, 24 Sep 2026 00:00:38 +0000 https://intelligentartifact.com/posts/ai-coding-rate-limits-are-ridiculous-now/ Medin hit the $200 Claude Max and $200 Codex Pro limits days before reset; the fix is model routing — most capable model for planning and review, cheap open model for implementation, roughly 4x cheaper with the same or better output. https://intelligentartifact.com/posts/bring-your-mcp-server-to-amazons-190k-hackathon/ Wed, 23 Sep 2026 13:54:24 +0000 https://intelligentartifact.com/posts/bring-your-mcp-server-to-amazons-190k-hackathon/ Amazon made MCP the standard for Alexa+ integrations; the Build, Ship, Shape hackathon covers Fire TV, Alexa+, Ring and Bee; the Alexa+ track takes an MCP server or Agent Skill with a simulated web-app stand-in; $190K in cash and AWS credits; submissions close Oct 23. https://intelligentartifact.com/posts/claude-opus-5-5-is-here-is-claude-finally-back/ Tue, 22 Sep 2026 16:33:00 +0000 https://intelligentartifact.com/posts/claude-opus-5-5-is-here-is-claude-finally-back/ Peter Yang stress-tests the new Opus on five tasks: a Golden Gate Bridge 3D flyover in Blender, a playable Soaring Over the World ride artifact, stroke-by-stroke impressionist painting, Claude Design inside Claude Code, and frame-by-frame video editing - plus the personality prompt that Opus 5 failed. https://intelligentartifact.com/posts/what-engineers-actually-do-now-that-ai-writes-the-code/ Mon, 21 Sep 2026 01:00:28 +0000 https://intelligentartifact.com/posts/what-engineers-actually-do-now-that-ai-writes-the-code/ Murali Swaminathan, CTO of Freshworks: 70%+ of net-new code is AI-written, commits capped at 500 lines because review is the new bottleneck, deflection moved from 40% to the high 70s, anything under 50% confidence goes back to a human, and agents get priced per session instead of per seat. https://intelligentartifact.com/posts/how-to-save-money-now-with-chatgpt-finances/ Sun, 20 Sep 2026 13:00:13 +0000 https://intelligentartifact.com/posts/how-to-save-money-now-with-chatgpt-finances/ Ethan Bloch, product lead for ChatGPT Finances, demos a 90-day subscription audit that emails the biller for you, tax optimization, ETF fee swaps, credit-card reward analysis, and interactive decision sites for rent-vs-buy and taking time off. https://intelligentartifact.com/posts/meta-muse-ai-agent-saved-me-800-a-year/ Fri, 18 Sep 2026 19:38:10 +0000 https://intelligentartifact.com/posts/meta-muse-ai-agent-saved-me-800-a-year/ Peter Yang's hands-on tour of Meta's Muse: $40/month off AT&T by finding an autopay discount, an agent that phones Comcast and negotiates in its own voice, native connectors to Meta's apps, a personalized feed with no ads yet, habit artifacts with streaks, and Marketplace listings it can haggle over. https://intelligentartifact.com/posts/building-a-personal-agent-that-actually-works/ Fri, 18 Sep 2026 17:51:04 +0000 https://intelligentartifact.com/posts/building-a-personal-agent-that-actually-works/ Sentience founding engineer Ahmet İlten on the four principles behind their personal-agent product: complexity masks the real problem, start from the user experience and work backwards, keep the system prompt visible as one monster you can stare at, and run evals before every change. https://intelligentartifact.com/posts/what-a-forward-deployed-engineer-is/ Thu, 17 Sep 2026 00:16:24 +0000 https://intelligentartifact.com/posts/what-a-forward-deployed-engineer-is/ Ali Parandeh on why heavy industry is 2-3 years behind on AI, why Copilot is the floor and not the strategy, bespoke predictive-maintenance models on bespoke sensor data, the dark-room-with-a-lantern case for time-boxed AI R&D, the four ways agent projects fail, scaling consulting through software and forward deployed engineers, and why handcrafted work gets more valuable. https://intelligentartifact.com/posts/you-built-your-ai-second-brain-now-what/ Thu, 17 Sep 2026 00:00:25 +0000 https://intelligentartifact.com/posts/you-built-your-ai-second-brain-now-what/ Cole Medin on turning a personal AI second brain into a team brain: one documents table, domain labels applied at ingestion, row-level permissions enforced inside the database behind a remote MCP server, and hybrid keyword + semantic retrieval. https://intelligentartifact.com/posts/how-i-automated-90-percent-of-my-content-workflow/ Wed, 16 Sep 2026 13:00:34 +0000 https://intelligentartifact.com/posts/how-i-automated-90-percent-of-my-content-workflow/ Peter Yang's 15-step podcast pipeline, split into three ChatGPT Skills (prep, edit, production) that call each other; pastes his manual edits back into the skill as a numbered diff so it one-shots next time. https://intelligentartifact.com/posts/evals-for-ai-writing/ Tue, 15 Sep 2026 21:30:37 +0000 https://intelligentartifact.com/posts/evals-for-ai-writing/ Three model-written X posts about the same document-QA pipeline, judged by reading the drafts aloud. The ones that won carried a real number and one fewer fact than the rest. https://intelligentartifact.com/posts/putting-claudes-ai-slop-solution-to-the-test/ Tue, 15 Sep 2026 21:30:32 +0000 https://intelligentartifact.com/posts/putting-claudes-ai-slop-solution-to-the-test/ Anthropic's fix for mannered prose is itself written in mannered prose. Hamel Husain and Isaac Flath run it side by side against a plain-writing prompt and a no-prompt baseline on the same question, then judge the drafts by reading them out loud. https://intelligentartifact.com/posts/my-new-favorite-skill-claude-code-drives-my-whole-computer/ Tue, 15 Sep 2026 00:00:10 +0000 https://intelligentartifact.com/posts/my-new-favorite-skill-claude-code-drives-my-whole-computer/ Cole Medin's 'drive screen' skill: ~400 lines, no harness, no extra installs; morning setup in 60 seconds; hard rules + control loop + a custom CLI for determinism; prompt-injection caveat and why he now trusts computer use. https://intelligentartifact.com/posts/why-the-future-of-content-is-born-multilingual/ Sun, 13 Sep 2026 18:01:28 +0000 https://intelligentartifact.com/posts/why-the-future-of-content-is-born-multilingual/ Smartling's VP of AI Olga Beregovaya on why one-to-one translation is dying, generating target content straight from briefs instead of a source, why models hallucinate more in under-resourced languages, interpretation outliving translation, translateese and modelese, the build-versus-buy line, and the 12 metrics her team scores translation quality with. https://intelligentartifact.com/posts/stop-building-ai-agents-build-ai-employees-instead/ Sun, 13 Sep 2026 13:00:14 +0000 https://intelligentartifact.com/posts/stop-building-ai-agents-build-ai-employees-instead/ Brex CEO Pedro Franceschi on scoping agents as virtual employees with a job, skills, manager and budget — the Jim recruiting demo, CrabTrap's LLM-as-a-judge proxy, Magpie for token spend, and the OpenClaw harness he runs his own life on. https://intelligentartifact.com/posts/no-ai-is-not-autonomously-hacking/ Sun, 13 Sep 2026 08:30:00 -0400 https://intelligentartifact.com/posts/no-ai-is-not-autonomously-hacking/ Newport's explanation of the OpenAI/Hugging Face incident: an ordinary program looping an LLM's plausible suggestions, executed for days without a human watching — a bad architecture, not a model that woke up. Plus why the same property that makes chatbots confabulate makes them unfit to author executed actions. https://intelligentartifact.com/posts/gpt-6-astra-software-factory-remote-deploy/ Sat, 12 Sep 2026 13:27:24 +0000 https://intelligentartifact.com/posts/gpt-6-astra-software-factory-remote-deploy/ A step-by-step deploy guide for Cole Medin's open-source software factory: GitHub issue in, validated merged PR out, running 24/7 on a remote Ubuntu box with Codex on GPT-6 Astra. Plus his blunt read on the AGI hype — not AGI, but the first model he says actually gets him. https://intelligentartifact.com/posts/trying-the-new-claude-eval-tool/ Fri, 11 Sep 2026 22:19:39 +0000 https://intelligentartifact.com/posts/trying-the-new-claude-eval-tool/ Hamel Husain streams Anthropic's new `claude plugin eval` against a plain-writing skill and calls it a failure: the eval it generates is one ablation against the skill's own rules, the numbers have no provenance, and it asks you for exactly the error analysis that is the hard part. https://intelligentartifact.com/posts/stop-competing-on-features-ai-agents-rob-kaminski/ Thu, 10 Sep 2026 01:56:38 +0000 https://intelligentartifact.com/posts/stop-competing-on-features-ai-agents-rob-kaminski/ Fletch PMM co-founder Rob Kaminski does a live positioning teardown of an AI agent startup on TwoSetAI: the three category strategies, why category creation is the trap founders overrate, why stacking features makes you forgettable, and why the real failure is refusing to choose. https://intelligentartifact.com/posts/security-for-ai-coding-deterministic-gates-cole-medin/ Thu, 10 Sep 2026 00:00:20 +0000 https://intelligentartifact.com/posts/security-for-ai-coding-deterministic-gates-cole-medin/ Cole Medin on why a second review agent is not a security process: coding agents ship vulnerabilities two ways, are trained to cut corners, and sometimes notice a flaw and ship it anyway. His fix is a deterministic gate — a real scanner wired into the workflow that the agent cannot skip and must iterate against until green. https://intelligentartifact.com/posts/safest-way-let-ai-coding-agents-run-real-infrastructure/ Tue, 08 Sep 2026 17:00:09 +0000 https://intelligentartifact.com/posts/safest-way-let-ai-coding-agents-run-real-infrastructure/ Cole Medin's pattern for letting coding agents operate real infrastructure without ever holding credentials: an orchestrator wraps the agent, exposes an allowlist of Git-managed workflows, and keeps every execution observable. A Kestra-sponsored ~2-minute spotlight. https://intelligentartifact.com/posts/vertical-ai-wedge-hiding-in-25-year-old-software/ Mon, 07 Sep 2026 04:02:19 +0000 https://intelligentartifact.com/posts/vertical-ai-wedge-hiding-in-25-year-old-software/ Rec Technologies CEO Birju Kadakia (early Uber, ran Uber Eats worldwide, product at The Athletic) on the vertical AI wedge in recreation tech — agents that read city policies and write deterministic refund code, skills-versus-workflows architecture, hallucination guardrails with real accuracy numbers, and hiring engineers who act like engineering managers. Interviewed by Angelina on TwoSetAI. https://intelligentartifact.com/posts/ai-makes-cheating-easy-sue-khim/ Sun, 06 Sep 2026 13:00:08 +0000 https://intelligentartifact.com/posts/ai-makes-cheating-easy-sue-khim/ Brilliant CEO Sue Khim on why students mostly use AI to cheat today, her AI tutor Cooji that refuses to hand over answers or explanations, and why the most defensible AI products live in domains the frontier labs can't RL on. https://intelligentartifact.com/posts/gpt-6-astra-4-amazing-games-you-can-build-with-blender-and-godot/ Sat, 05 Sep 2026 16:30:02 +0000 https://intelligentartifact.com/posts/gpt-6-astra-4-amazing-games-you-can-build-with-blender-and-godot/ Peter Yang builds four games in one night with GPT-6 Astra on the $20 ChatGPT Plus plan — Star Fox-style shooter, train FPS, Starcraft-like RTS, and a roguelike deckbuilder — using free Blender/Godot MCP servers, concept art, and mostly lazy voice feedback. https://intelligentartifact.com/posts/the-biggest-opportunities-in-ai-arent-where-you-think/ Fri, 04 Sep 2026 11:48:00 +0000 https://intelligentartifact.com/posts/the-biggest-opportunities-in-ai-arent-where-you-think/ Andrew Ng on the Silicon Valley Girl podcast: why the AI doom drumbeat is incumbent-driven regulatory capture, why AI doing 30-40% of job tasks makes the human 60-70% more valuable, why LLMs as commonly used are terrible for learning (and his new Learn Vector 1-to-1 tutoring bet), the context advantage that keeps human judgment relevant, and the 'product management bottleneck' he says is now the real constraint on building. https://intelligentartifact.com/posts/how-to-build-and-evaluate-search-agents/ Thu, 03 Sep 2026 21:30:03 +0000 https://intelligentartifact.com/posts/how-to-build-and-evaluate-search-agents/ Nandan Thakur (BEIR, MIRACL, TREC-RAG; now Microsoft Research India) on agentic search: BrowseComp-Plus as a reproducible eval, why the retriever moves accuracy more than the model does (60% → 88% on the same LLM), ORBIT's zero-budget 20k-question synthetic data pipeline, and HawkEye trajectory analysis for the leaderboard trap where 95% accuracy hides 210 search calls. https://intelligentartifact.com/posts/pricing-ai-agent-companies/ Thu, 03 Sep 2026 02:43:10 +0000 https://intelligentartifact.com/posts/pricing-ai-agent-companies/ Former CRO Jenée Hall on pricing AI agent products — the five pricing layers from per-seat access to outcome-based fees, why token-style usage pricing misleads, and how to test price like a hypothesis. Interviewed by Angelina on TwoSetAI. https://intelligentartifact.com/posts/how-to-stop-building-products-nobody-wants/ Wed, 02 Sep 2026 20:30:35 +0000 https://intelligentartifact.com/posts/how-to-stop-building-products-nobody-wants/ Teresa Torres (Continuous Discovery Habits) on why 'talk to your customers' fails for engineers, story-based interviewing as the reliable feedback loop, the Opportunity Solution Tree, how AI synthesis and her Vistily partnership put evals at the center of discovery, and a three-week eval war story about upstream errors and counterbalancing judges. https://intelligentartifact.com/posts/instinct-vs-grok-bot-vs-chatgpt-vs-hermes-which-ai-agent-can-you-trust/ Wed, 02 Sep 2026 13:00:18 +0000 https://intelligentartifact.com/posts/instinct-vs-grok-bot-vs-chatgpt-vs-hermes-which-ai-agent-can-you-trust/ Peter Yang runs four personal AI agents at once — Instinct, Grok Bot, ChatGPT/Codex, and open-source Hermes — and stress-tests what you're really handing over: passwords, 2FA codes, prompt-injection surface, and whether you can ever get the data back. https://intelligentartifact.com/posts/11-tiny-coding-agent-fixes-stupid-payoff/ Tue, 01 Sep 2026 17:06:40 +0000 https://intelligentartifact.com/posts/11-tiny-coding-agent-fixes-stupid-payoff/ Cole Medin's 11 small, high-leverage fixes for making any coding agent more reliable — from writing for the agent (not the human) and keeping rules under ~200 lines, to moving guarantees into deterministic hooks and never letting the writer approve its own work. https://intelligentartifact.com/posts/write-change-recall-forget-mongodb-agent-memory/ Tue, 01 Sep 2026 09:26:38 +0000 https://intelligentartifact.com/posts/write-change-recall-forget-mongodb-agent-memory/ MongoDB's field CTO of AI argues agent performance — especially cost-adjusted — is a retrieval problem, not a model problem: a history of constraints, why embeddings aren't commoditized, and the write/change/recall/forget memory loop. https://intelligentartifact.com/posts/stop-shipping-ai-nobody-can-verify/ Tue, 01 Sep 2026 01:59:27 +0000 https://intelligentartifact.com/posts/stop-shipping-ai-nobody-can-verify/ Hamel Husain on why 'it's hard to eval' is a product smell, verification-first design (the data agent, workers' comp report, and PE lesson planner redesigns), sharing skill shapes not skills, transition failure matrices, and why data science is more valuable than ever in the agentic era. https://intelligentartifact.com/posts/stop-picking-embedding-models-off-the-mteb-leaderboard/ Mon, 31 Aug 2026 21:30:09 +0000 https://intelligentartifact.com/posts/stop-picking-embedding-models-off-the-mteb-leaderboard/ Radu, search engineer at Vespa, on why leaderboard picks leave cost, latency, and quality on the table — quantization, Matryoshka dims, tuning with Vespa Embed, and cheap-embedder + re-ranker architectures. https://intelligentartifact.com/posts/next-token-ep-05-inference-economics/ Mon, 31 Aug 2026 14:00:53 +0000 https://intelligentartifact.com/posts/next-token-ep-05-inference-economics/ Cloudflare AI product lead Michelle Chen explains model launches, GPU economics, licensing, and why cheap inference subscriptions may tighten. https://intelligentartifact.com/posts/claude-cowork-system-week-of-pm-work-in-a-day/ Mon, 31 Aug 2026 12:00:39 +0000 https://intelligentartifact.com/posts/claude-cowork-system-week-of-pm-work-in-a-day/ Daniel Bloom, a PM at Melio, walks through his self-improving Claude Cowork system: a Notion board his agent builds and manages for him, proactive context acquisition ('what does this term mean?'), a weekly prep and daily brief, a self-improvement loop that learns from his edits — and the Workstation plugin that onboards the whole company in 15 minutes. https://intelligentartifact.com/posts/the-one-skill-that-survives-the-ai-shift/ Sun, 30 Aug 2026 23:00:23 +0000 https://intelligentartifact.com/posts/the-one-skill-that-survives-the-ai-shift/ Vectara's Ofer Mendelevitch (Hands-On RAG for Production) on building RAG systems that actually work at scale — retrieval, multimodal data, knowledge graphs, evals without golden answers — and why the skill that survives the AI shift is directing agents, not writing code. https://intelligentartifact.com/posts/how-non-coders-are-vibe-coding-100k-businesses-with-ai/ Sun, 30 Aug 2026 13:00:17 +0000 https://intelligentartifact.com/posts/how-non-coders-are-vibe-coding-100k-businesses-with-ai/ Replit's head of engineering on non-coders building real businesses with AI, the cost-of-code-zero test for what SaaS survives, and why app-layer companies are thriving. https://intelligentartifact.com/posts/ais-third-era-the-rise-of-persistent-ai-coworkers/ Sun, 30 Aug 2026 12:30:33 +0000 https://intelligentartifact.com/posts/ais-third-era-the-rise-of-persistent-ai-coworkers/ Tara Seshan — OpenAI's product lead for Codex and ChatGPT Work — maps the third era of AI products (after chat and coding agents): persistent coworkers you steer, why ambition is the new differentiator, and why writing-as-thinking is the craft that survives. https://intelligentartifact.com/posts/chatgpt-vs-claude-vs-grok-vs-gemini-best-ai-for-10-use-cases/ Wed, 26 Aug 2026 13:00:07 +0000 https://intelligentartifact.com/posts/chatgpt-vs-claude-vs-grok-vs-gemini-best-ai-for-10-use-cases/ Peter Yang's head-to-head across design, writing, planning, coding, browser use, voice, image/video gen, and personal agents — with live demos and a clear overall winner. https://intelligentartifact.com/posts/dont-build-agents-build-environments-instead/ Tue, 25 Aug 2026 21:30:10 +0000 https://intelligentartifact.com/posts/dont-build-agents-build-environments-instead/ The hard part of background agents is the background: dev boxes over sandboxes, sessions over jobs, and keeping the agent in the control plane away from the risky work. https://intelligentartifact.com/posts/how-to-build-better-ai-evals-with-claude-code/ Sun, 23 Aug 2026 13:00:04 +0000 https://intelligentartifact.com/posts/how-to-build-better-ai-evals-with-claude-code/ Shreya Shankar and Hamel Husain walk through the practical evals loop: top-down vs bottom-up criteria, an open-source Claude Code "error discovery" workflow that turns your taste into a rubric, and why automated eval tools get you a baseline but never replace reading your own data. https://intelligentartifact.com/posts/how-multi-vector-retrieval-works-at-scale/ Fri, 21 Aug 2026 21:30:02 +0000 https://intelligentartifact.com/posts/how-multi-vector-retrieval-works-at-scale/ Why single-vector embeddings fail agentic retrieval, how late-interaction multi-vector scoring preserves low-level detail, and how sparse encoding makes it fast enough for production. https://intelligentartifact.com/posts/how-to-turn-evals-into-a-better-model/ Mon, 17 Aug 2026 20:30:11 +0000 https://intelligentartifact.com/posts/how-to-turn-evals-into-a-better-model/ Evals are the bottleneck: the three parts of an evaluation, the hidden variables that skew scores, and when to reach for fine-tuning and RL instead of prompt tweaks. https://intelligentartifact.com/posts/next-token-ep-04-alignment-agent-verification/ Mon, 17 Aug 2026 17:25:16 +0000 https://intelligentartifact.com/posts/next-token-ep-04-alignment-agent-verification/ Dillon Mulroy, Rhys Sullivan, and Sunil Pai debate AI containment, then inspect a coding workflow built around scoped access and visible end-to-end tests. https://intelligentartifact.com/posts/grok-bot-5-must-try-use-cases-for-work-and-life/ Mon, 17 Aug 2026 17:09:39 +0000 https://intelligentartifact.com/posts/grok-bot-5-must-try-use-cases-for-work-and-life/ A full tutorial on Grok Bot's dedicated cloud computer: advisor, YouTube researcher, X Scout, digital Marie Kondo, and travel concierge — plus the trust question. https://intelligentartifact.com/posts/how-i-run-my-content-business-with-codex/ Sun, 16 Aug 2026 13:00:26 +0000 https://intelligentartifact.com/posts/how-i-run-my-content-business-with-codex/ Riley Brown's full content stack on Codex: skills for research, hooks, thumbnails, and diagrams — plus his test-based, outcome-driven way of improving skills. https://intelligentartifact.com/posts/cut-llm-classification-costs-by-90/ Wed, 12 Aug 2026 17:07:59 +0000 https://intelligentartifact.com/posts/cut-llm-classification-costs-by-90/ A live whiteboard lecture on model cascades: send every record to a cheap proxy model first, accept its answer when confidence is high, route the rest to the expensive model — and pick the threshold from a labeled sample to hit your accuracy target at minimum cost. https://intelligentartifact.com/posts/llm-knowledge-bases-practical-guide/ Wed, 12 Aug 2026 17:00:22 +0000 https://intelligentartifact.com/posts/llm-knowledge-bases-practical-guide/ A practical LLM knowledge-base pipeline: voice-dictated raw notes, agent skills that enrich and backlink them, generated wikis, nightly cloud automation, and agent-built graph visualizations. https://intelligentartifact.com/posts/agents-codebases-and-teams/ Mon, 10 Aug 2026 17:03:17 -0700 https://intelligentartifact.com/posts/agents-codebases-and-teams/ The enterprise adoption cycle, the fear×confidence axes, and a concrete playbook for making coding agents work for a whole team. https://intelligentartifact.com/posts/next-token-ep3-burnout-uncertainty/ Mon, 10 Aug 2026 22:07:43 +0000 https://intelligentartifact.com/posts/next-token-ep3-burnout-uncertainty/ Dillon Mulroy, Rhys Sullivan, and Sunil Pai discuss AI burnout, lost collaboration, and the parts of making software that still bring joy. https://intelligentartifact.com/posts/5-rules-for-building-ai-agents-that-work-in-production/ Sun, 09 Aug 2026 13:00:34 +0000 https://intelligentartifact.com/posts/5-rules-for-building-ai-agents-that-work-in-production/ Linear's Nan Yu and Jacob Shumway on the Linear Agent: the skills architecture, evals that grow from usage, minimal instruction, and agents tied to humans. https://intelligentartifact.com/posts/how-to-use-open-models-effectively/ Fri, 07 Aug 2026 21:30:06 +0000 https://intelligentartifact.com/posts/how-to-use-open-models-effectively/ Zach Mueller (Lambda) on when open models beat APIs: the current open-model landscape, token-speed targets, quantization trade-offs, and why open weights are good enough for ~90% of tasks for ~90% of people. https://intelligentartifact.com/posts/how-to-build-launch-an-ai-startup-with-claude-code/ Thu, 06 Aug 2026 12:05:24 -0700 https://intelligentartifact.com/posts/how-to-build-launch-an-ai-startup-with-claude-code/ A complete Product OS walkthrough: define, design, develop, and distribute a real software product with Claude Code — with four case studies of non-technical founders making real money. https://intelligentartifact.com/posts/stanford-cs329a-self-improving-ai-agents/ Mon, 03 Aug 2026 13:00:00 -0400 https://intelligentartifact.com/posts/stanford-cs329a-self-improving-ai-agents/ The opening lecture of Stanford CS329A: scaling laws, inference-time scaling, reasoning models, and the self-improving loop that powers agents. https://intelligentartifact.com/posts/hermes-cofounder-on-building-an-ai-agent-that-improves-itself/ Sun, 02 Aug 2026 13:00:12 +0000 https://intelligentartifact.com/posts/hermes-cofounder-on-building-an-ai-agent-that-improves-itself/ Nous Research's Karan Malhotra on why Hermes outperforms native harnesses, reward hacking and sycophancy, the Hermes Curator, and a Sonic Chao Garden mod built entirely by his agent. https://intelligentartifact.com/posts/jev-whats-next-after-rlhf/ Fri, 31 Jul 2026 16:30:06 -0700 https://intelligentartifact.com/posts/jev-whats-next-after-rlhf/ Diogo Almeida argues that pleasing a human and running reliable software are different objectives. His case for moving beyond AI assistance—and why he says Jev's approach is not simply RLVR. https://intelligentartifact.com/posts/how-to-build-agents-that-answer-data-questions/ Fri, 31 Jul 2026 21:30:38 +0000 https://intelligentartifact.com/posts/how-to-build-agents-that-answer-data-questions/ The DAB benchmark for data agents: why text-to-SQL isn't enough, the four real-world data challenges (messy joins, multi-database, free text, domain knowledge), and why frontier agents only pass 57% of the time. https://intelligentartifact.com/posts/how-to-make-codex-run-itself/ Mon, 27 Jul 2026 21:30:14 +0000 https://intelligentartifact.com/posts/how-to-make-codex-run-itself/ Codex's hidden superpower: threads that spawn threads, talk to each other, and orchestrate themselves. Hamel demos running 16 parallel coding tasks with computer use and mobile control. https://intelligentartifact.com/posts/how-to-choose-the-right-ocr-model/ Fri, 24 Jul 2026 21:30:07 +0000 https://intelligentartifact.com/posts/how-to-choose-the-right-ocr-model/ A practical framework for picking an OCR model: text-blocks vs document structure, API vs self-host, and why you should test on your own data instead of trusting benchmarks. https://intelligentartifact.com/posts/next-token-ep-02-human-owned-agent-workflows/ Thu, 23 Jul 2026 03:48:58 +0000 https://intelligentartifact.com/posts/next-token-ep-02-human-owned-agent-workflows/ Dillon Mulroy shows how Pi, Plannotator, and type-driven plans keep him involved in agent-written software. https://intelligentartifact.com/posts/claude-design-easy-for-beginners/ Tue, 21 Jul 2026 06:00:15 -0700 https://intelligentartifact.com/posts/claude-design-easy-for-beginners/ The anti-generic Claude Design workflow: prepare three files (design.md → design system → template) so every deck starts on-brand and every feedback compounds into future designs. https://intelligentartifact.com/posts/claude-design-complete-guide/ Sun, 19 Jul 2026 11:45:51 -0700 https://intelligentartifact.com/posts/claude-design-complete-guide/ Full Claude Design platform walkthrough: expanded templates, bundled usage, design systems for on-brand output, and a motion-graphics-for-videos use case that is genuinely surprising. https://intelligentartifact.com/posts/how-to-build-ai-evals/ Fri, 17 Jul 2026 00:00:00 +0000 https://intelligentartifact.com/posts/how-to-build-ai-evals/ Lucas Rocha, an engineer at Brazilian edtech Nova Escola and alum of Hamel Husain's AI Evals course, tells his evals rollout story backwards: from a team that now runs LLM judges with no tickets and no engineer in the loop, back to the messy first spreadsheet and the three barriers — data, methodology, and judgment — that every team hits along the way. https://intelligentartifact.com/posts/wayfinder-demo/ Mon, 13 Jul 2026 09:25:39 -0700 https://intelligentartifact.com/posts/wayfinder-demo/ Wayfinder is Matt Pocock's pre-spec orchestration tool: it charts a map of parallel decision/research/prototype tickets, spawns agents, and resolves open questions into a spec — demonstrated live building a TikTok creator feature. https://intelligentartifact.com/posts/how-to-reduce-llm-latency/ Sat, 11 Jul 2026 00:00:00 +0000 https://intelligentartifact.com/posts/how-to-reduce-llm-latency/ Abi Aryan breaks down where LLM latency actually goes: the compute-bound prefill phase vs the memory-bandwidth-bound decode phase, and why decode — not prefill — dominates latency and cost, especially in multi-step agentic systems. A live Colab walkthrough with TinyLlama on a T4 measures both phases across chat, RAG, creative, and agentic request shapes. https://intelligentartifact.com/posts/how-to-build-ai-that-earns-user-trust/ Tue, 07 Jul 2026 00:00:00 +0000 https://intelligentartifact.com/posts/how-to-build-ai-that-earns-user-trust/ Before worrying about evals, ask if you are building the right thing: AI that dumps an unverifiable answer creates more work. Hamel walks through design patterns — provenance, progressive disclosure, expert signals, modular steps — across three worked examples. https://intelligentartifact.com/posts/how-to-run-ai-coding-sessions-from-your-phone/ Mon, 06 Jul 2026 00:00:00 +0000 https://intelligentartifact.com/posts/how-to-run-ai-coding-sessions-from-your-phone/ A walkthrough of Codex desktop app remote control: connect your agentic-coding servers, kick off sessions from your phone, and watch agents work anywhere — with live session views, subagent summaries, and follow-up prompts. https://intelligentartifact.com/posts/how-to-automate-ai-evals-correctly/ Fri, 03 Jul 2026 21:30:24 +0000 https://intelligentartifact.com/posts/how-to-automate-ai-evals-correctly/ Part 1 of Hamel and Shreya's AI product engineering series: the analyze → measure → improve eval lifecycle, and three mistakes to avoid when using AI to automate evals. https://intelligentartifact.com/posts/next-token-ep-01-enable-my-agent/ Fri, 03 Jul 2026 18:52:12 +0000 https://intelligentartifact.com/posts/next-token-ep-01-enable-my-agent/ Dillon Mulroy, Rhys Sullivan, and Sunil Pai argue for products that serve a customer's chosen agent. Their examples connect APIs, documentation, review loops, cloud environments, and burnout. https://intelligentartifact.com/posts/how-to-hire-an-ai-consultant-the-right-way/ Thu, 02 Jul 2026 00:00:00 +0000 https://intelligentartifact.com/posts/how-to-hire-an-ai-consultant-the-right-way/ Hamel argues that hiring a consultant to implement AI and walk away is almost always a mistake — the underlying problems remain and the AI itself is designed to remove the middleman. Consultants work only for education or when they have skin in the game. https://intelligentartifact.com/posts/how-to-eval-an-ai-product-that-seems-impossible-to-eval/ Mon, 29 Jun 2026 00:00:00 +0000 https://intelligentartifact.com/posts/how-to-eval-an-ai-product-that-seems-impossible-to-eval/ When a product seems impossible to eval, that is usually a sign the product itself is weak. Hamel suggests infusing user-facing signals into the product so users — and you — can assess quality. https://intelligentartifact.com/posts/next-token-ep-00-software-quality/ Fri, 26 Jun 2026 21:52:49 +0000 https://intelligentartifact.com/posts/next-token-ep-00-software-quality/ Dillon Mulroy, Rhys Sullivan, and Sunil Pai ask why more generated code has not produced better software. They compare architecture, token costs, model access, and autonomous loops. https://intelligentartifact.com/posts/if-you-cant-eval-your-ai-your-users-cant-trust-it/ Fri, 26 Jun 2026 00:00:00 +0000 https://intelligentartifact.com/posts/if-you-cant-eval-your-ai-your-users-cant-trust-it/ Hamel Husain counters the 'evals take too long' objection with one principle: if you can't eval your product, your users can't either — so evals are how you figure out how to convey trust in AI answers. https://intelligentartifact.com/posts/why-theres-no-llm-judge-you-can-trust-100-of-the-time/ Mon, 22 Jun 2026 00:00:00 +0000 https://intelligentartifact.com/posts/why-theres-no-llm-judge-you-can-trust-100-of-the-time/ Hamel Husain explains how to scientifically measure an LLM judge's noise against ground-truth human labels — and why every LLM judge is a black-box classifier with edge cases, so you have to decide how much noise is tolerable. https://intelligentartifact.com/posts/why-ai-rating-scales-make-it-harder-to-ship/ Sun, 21 Jun 2026 00:00:00 +0000 https://intelligentartifact.com/posts/why-ai-rating-scales-make-it-harder-to-ship/ Hamel Husain argues that ROUGE/BLEU string-similarity scores and 1-to-10 rating scales are holdovers from traditional NLP that make evals harder to act on — nobody knows what a 4.2 means, and binary pass/fail evals are what actually let you ship. https://intelligentartifact.com/posts/why-the-1-to-5-scale-is-where-ai-evals-break-down/ Sat, 20 Jun 2026 00:00:00 +0000 https://intelligentartifact.com/posts/why-the-1-to-5-scale-is-where-ai-evals-break-down/ Hamel Husain explains why he converts every 1-to-5 rating scale eval into binary pass/fail checks, scoping each failure into a specific, actionable criterion instead of hiding noise behind middle values. https://intelligentartifact.com/posts/the-ai-testing-framework-every-business-needs/ Mon, 20 Apr 2026 22:15:49 +0000 https://intelligentartifact.com/posts/the-ai-testing-framework-every-business-needs/ Hamel Husain on evals for non-experts: why generic metric dashboards actively hurt you, how error analysis beats top-down guesswork, what guardrails and MCPs actually are, and the argument that AI competency can never be outsourced. https://intelligentartifact.com/posts/why-opus-4-5-most-influential-ai-model/ Wed, 03 Dec 2025 08:17:37 -0800 https://intelligentartifact.com/posts/why-opus-4-5-most-influential-ai-model/ Paul Ford (former Harper's editor, co-founder of Abort) and Dan Shipper process the week Opus 4.5 landed in Claude Code — the step change, the grief, the discourse, and what actually matters.