Articles
Industry news, technical articles, and product introductions
📚 Claude Tutorials Hub
40+ step-by-step Claude guides — prompt engineering, Claude Code, API, agents. Browse by topic →
Loading...
Industry news, technical articles, and product introductions
📚 Claude Tutorials Hub
40+ step-by-step Claude guides — prompt engineering, Claude Code, API, agents. Browse by topic →
Loading...
On a third-party model, Claude Code auto mode sends one extra classifier request per side-effecting action, from your session model to the same backend: a 132,470-character system prompt, about 29.7K input tokens per check. When it fails, you see "xxx is temporarily unavailable, so auto mode cannot determine the safety of Bash". We injected faults and recorded each message: 500 (server error), 429 (rate-limited), 529 (overloaded) and connection resets (connection failed) are retried 5 times; no reply in 60 s gives (timed out). **No parentheses means a 4xx rejection: tried once, and retrying never helps.** A reply with no verdict gives "could not evaluate"; three in a row bring back manual approval. CLAUDE_CODE_AUTO_MODE_MODEL has no effect. Claude Code 2.1.285, real DeepSeek v4-pro and MiMo v2.5 backends.
Claude Code decides a request was too long by matching the error text. If the backend says prompt is too long or input is too long for requested model, it auto-compacts the conversation and retries — invisible to you. DeepSeek and OpenAI-style gateways say This model's maximum context length is …, which it doesn't recognize: you get API Error: 400 on every turn. Manual /compact works; the better fix is to declare the real window with CLAUDE_CODE_MAX_CONTEXT_TOKENS (non-claude- model IDs) or CLAUDE_CODE_AUTO_COMPACT_WINDOW (claude- IDs) so it compacts before hitting the limit. Tested on Claude Code 2.1.285 against a local stub.
DeepSeek-V4-Pro-0813 posted a Terminal-Bench score 0.1 behind Fable 5, then scored 53 on Artificial Analysis — one point above its own small model — before the announcement vanished that afternoon. The Hugging Face commit log tells a different story than 'the model is bad.'
Netlify ran the same coffee-shop prompt through 11 frontier models using its open-sourced AXIS framework. Credit spend ranged from 2.4 to 519 — and the price tag turned out to be the least interesting part.
Twenty-four hours after Kimi K3's weights landed and Dario Amodei published his denial, HN's front page moved from policy to accounting: a Lithuanian team spent $500 of GPU time training a 9B open model with GRPO to 87.3% on catalog review — beating GPT-5.5, Gemini 3.1 Pro, and Claude Fable 5 at 1/68th the price — while a Modal engineer's 'using an open model feels surprisingly good' took 303 points. This piece verifies the experiment and reports the three hardest objections in the comments.
In a rare 4-hour investor meeting, DeepSeek founder Liang Wenfeng shared the company's founding vision, open-source strategy, API pricing logic, AGI roadmap, organizational philosophy, and views on the China-US AI gap. Here are 10 key insights distilled from the conversation.