AI Coding Live News

Independent benchmarker Artificial Analysis announced on X on November 4 (17:34 UTC) a new version of its API performance benchmarking: the headline metric moves from output speed to Time per Task, the time to finish one Intelligence Index task (output tokens per task divided by end-to-end output speed). It covers about 1,000 serverless endpoints, measures speed from sending the request to the final token, and adds multi-turn agentic coding and knowledge-work workloads. Per its data, GPT-6 Astra at max effort runs at 51 tokens/s yet finishes a task in about 17 minutes, against about 26 for Claude Opus 5.5 (max) and about 29 for Gemini 4 Carbon (high).

Shopify distinguished engineer Burke Libbey posted on November 1 that moving to a monorepo has been a boon for agents at Shopify; it needs thoughtful tooling and has downsides that take effort to mitigate, but he would not go back. He was replying to Darren Shepherd, who said a day earlier that he hates the idea that monorepos are great for agents. Shopify CEO Tobi Lütke then quoted Burke and recalled Mikhail Parakhin telling him that every engineer hates the idea of moving to a monorepo, yet once it is there no engineer would want to work somewhere without one. Tobi's post drew about 1,115 likes, 454 bookmarks and 89K views and set off a wide debate. These are practitioner opinions, not an official technical announcement.

A topic drawing heavy discussion on X: a new Associated Press feature reports that some AI companies are turning to religion as they work out how to teach chatbots right from wrong. On Nov 1 the market-news account unusual_whales relayed the report, noting that Anthropic says it has met with scholars, clergy, philosophers and ethicists from more than 15 religious and cross-cultural groups to help shape how Claude handles moral questions. The post drew about 880 likes, 162K views and 189 replies, and X listed the story among its trending news topics. The Anthropic effort itself is not new: the company described it in an official post on May 19. This is a write-up of the discussion, with opinions presented as opinions.

Anthropic published Claude Code v2.1.314 on GitHub at 01:06 UTC on Oct 30. The official CHANGELOG lists 119 entries, more than half of them fixes. The new features lean enterprise: permissions.blockWritesOutsideWorkingDirectories makes Write, Edit and NotebookEdit refuse paths outside the working directories in every permission mode; Claude apps gateway upstreams can be limited to IdP groups, and Bedrock upstreams can log which guardrail fired; idle compaction now also runs in VS Code and the Code tab of Claude Desktop. It also fixes sessions failing repeatedly when an admin caps effort, and claude -p exiting 0 with no output when startup failed.

Since Oct 21 many developers on X have complained that Claude Code was draining usage limits much faster. On Oct 28 (UTC) Boris Cherny, who leads Claude Code at Anthropic, replied on X that the team reviewed every session ID users shared, found no single root cause and no regression in Claude Code, and is rolling out fixes for a few smaller issues that made some sessions burn tokens faster. Most fast-drain cases traced back to one or two heavy sessions using xhigh effort, /goal, Workflows, Agent Teams or long SDK jobs.

Mistral AI announced on X on Oct 28 that its Responses API is in public preview, positioned as the interface for building agents on Mistral. The official docs say it uses the OpenAI Responses format, and each response's output array carries the models messages, its reasoning and its function calls as separate items, which is easier to handle step by step than Chat Completions. The preview is stateless, so the app keeps the conversation history and sends it back; it supports text, image and file input, JSON Schema structured output, streaming events, client-executed function calls, reasoning.effort, and token counting via POST /v1/responses/input_tokens. It is served in the EU and US on Mistral AI Cloud Inference. The same thread says Mistral now also serves DeepSeek V4.1 Flash (public preview) and GLM 5.3 Flash (generally available).

At 17:23 UTC on 2026-10-25, TypeScript educator Matt Pocock (@mattpocockuk, author of Total TypeScript and AI Hero) posted (post) that the next great "language for agents" should be as fast as Rust, have as little design space as Go, and have the strictest type/verification system ever written, calling Bend "an interesting first effort". When we pulled it, the post had about 3,130 likes, 84 reposts, 264 replies, 786 bookmarks and 220K views, and it reached X's trending stories. Mojo creator Chris Lattner replied (reply) recommending Mojo and suggesting "can target all hardware" be added to the list. This is an opinion debate, not a verified conclusion.

At 12:11 UTC on 2026-10-25, the Nanbeige LLM Lab of BOSS Zhipin (Kanzhun Limited) announced Nanbeige4.3-33B from its account @nanbeige (post), with the model and its Base version released as open weights on Hugging Face under Apache 2.0 (model card). It is a 33B dense model on a Llama-style architecture with a 512K context window, positioned as the teacher model of the Nanbeige4.3 series that will be distilled into smaller models such as Nanbeige4.3-3B. The official model card compares it with Qwen3.8-27B, Muse-Glimmer-30B and Gemma4-31B using the same harness at highest thinking effort: 80.9 on Terminal-Bench 2.1 (Qwen3.8-27B 73.0) and 65.5 on DeepSWE (42.5), but 60.3 on SWE-Bench Pro, slightly below Qwen's 61.7, and 84.8 on GDPval vs 86.4. All figures are self-reported and not yet independently reproduced.