Page 4 of 100
Deep dives into AI agents, coding tools, and building with LLMs.
1189 articles844 topics
DHS ordered DeepSeek products removed from US civilian agency IT. The scope reaches third-party products built on DeepSeek implementations - here is what that means for builders.
Which 429, 529 and 503 errors to retry across OpenAI, Claude, Gemini and Bedrock, how to read Retry-After, and a typed wrapper that skips quota errors.
Every scheduled AI model API shutdown through mid 2027 by month: GPT-4o on Jan 14, whisper-1 on Feb 26, Claude Sonnet 4.5 on Nov 30, plus how to migrate.
Microsoft Foundry retires codex-mini and Claude Haiku 4.5 on November 15, two gpt-chat-latest previews on November 17, and o1, o1-pro and five more o-series models on November 19, 2026. Dates, auto-upgrade rules, replacements, prices and the deployment change.
Amazon Bedrock ends Claude 3 Haiku, 3 Sonnet, 3.5 Sonnet, 3.5 Sonnet v2 and 3.7 Sonnet in seven Regions on November 13, 2026. The dates, the new model ids, the prices and the code change.
China drafted export controls on 23 AI technologies, including model weights. API use and already-public weights are exempt. What changes for builders on Qwen, DeepSeek and GLM.
Which embedding model to use in 2026: 20+ API and open-weight models compared on price per 1M tokens, dimensions, max input and license, with storage math.
The Gemini API shuts down two Live API preview models and three TTS preview models on November 17, 2026. Replacement ids, what changes in the session config and TTS request, prices before and after, and the code change.
How much VRAM a local LLM needs: Q4 weights are about 30% of BF16, plus a KV cache that grows per token. Real numbers from 8 GB to 256 GB.
Caching a shared prompt cut our worked example by about 78-80% on four models; batch takes 50% off at most providers but 40% at Moonshot and 20% at xAI. Only Anthropic, Fireworks and xAI say the two stack. The math, the assumptions and the quotes.
At the same 1K size label, per-image API prices run from $0.003 to $0.22. At 720p, video runs from $0.025 to $1.50 a second. The like-for-like math, the units that do not convert, what retires this week, and where the providers' own docs disagree.
Langfuse is part of ClickHouse, Promptfoo is part of OpenAI, Galileo is part of Cisco, Traceloop is joining ServiceNow, Helicone joined Mintlify and Humanloop shut down. Who owns what in October 2026, the dates the vendors state, and a portability checklist built on OTLP ingest, licenses and self-hosting.
Showing 37-48 of 1189 articles
Deep dives on AI agents, coding tools, and building with LLMs - delivered weekly. No spam.
Free forever. Unsubscribe anytime.
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
