{"date":"2026-11-01","title":"What happened in AI — Nov 1, 2026","generated_at":"2026-11-01T22:15:49Z","intro":["Coding-agent harness cost is the day's thread: the same model scored 82% or 65% on 21 MCP servers depending on the agent wrapped around it, and tooling to trim token spend is multiplying.","DeepSeek open-sourced a router-worker coding agent and its architecture, a direct open alternative to Claude Code."],"highlights":["Same Claude Haiku 5.5, 17 points apart: 82.0% via OpenCode vs 65.4% via Claude Code on 21 MCP servers.","DeepSeek open-sources dsh-superagent, a router-worker coding agent, plus its architecture.","Pi was the lightest of six coding-agent CLIs on per-job container overhead.","SWE-bench Verified 88.6% vs 59.1% best public SWE-bench Pro score: benchmark cliff for Opus 4.8.","Reviewing 1,700-line agent PRs needs reading order, not line-by-line diffs."],"article_count":25,"categories":[{"name":"Harness overhead is now a measurable cost","slug":"harness-overhead-measurable-cost","summary":"Four posts put numbers on what coding-agent harnesses spend: tokens, container start-up time, and MCP task accuracy.","articles":[{"title":"The tokens in your agent harness","summary":"Codex runs a background thread-naming call on every new session; the author reads the open-source Rust harness to show where tokens go.","source":"hackernews_ai","url":"https://armincat.com/articles/where-tokens-go","published":"2026-11-01T19:34:22Z"},{"title":"Which coding-agent CLI is best for headless workflow automation?","summary":"Six coding-agent CLIs benchmarked for per-job overhead in fresh containers: pi was lightest overall, Goose had the fastest median first response; task success is not measured.","source":"hackernews_ai","url":"https://aictrl.dev/blog/headless-coding-agent-cli-benchmark","published":"2026-11-01T18:42:17Z"},{"title":"Same model, different agent: 17 points apart on 21 MCP servers","summary":"Claude Haiku 5.5 answered 82.0% of tasks across 21 MCP servers via OpenCode but 65.4% via Claude Code; built-in tools the agent reaches for first explain the gap.","source":"hackernews_ai","url":"https://m3.sineframe.com/blog/same-model-different-agent","published":"2026-11-01T14:22:25Z"},{"title":"Context Mode – An Open-Source MCP Server That Reduces AI Coding Context Usage","summary":"Open-source MCP server that sandboxes tool output (claims a 98% reduction) and persists session memory across 17 platforms.","source":"hackernews_ai","url":"https://github.com/mksglu/context-mode","published":"2026-11-01T11:56:19Z"},{"title":"Codedict – a no-AI code index that cut my Claude Code tokens by 63%","summary":"Tree-sitter plus SQLite code index, no AI, that answers code questions up front; the author reports 63% fewer Claude Code tokens.","source":"hackernews_ai","url":"https://github.com/Marqueos/codedict","published":"2026-11-01T15:54:21Z"}]},{"name":"Agent workflows that keep humans on the decision","slug":"agent-workflows-human-decision","summary":"Teams are wrapping coding agents in review and gating loops so humans handle only the judgment calls.","articles":[{"title":"How I Review 2K Lines of AI Generated Code","summary":"Reviewing a 31-file, ~1,700-line agent PR with a two-sentence description: reading order matters more than line-by-line scrutiny.","source":"hackernews_ai","url":"https://bytesizedbets.com/p/how-to-review-a-2000-line-ai-written","published":"2026-11-01T16:30:21Z"},{"title":"Docsferatu: An agent that drafts docs PRs while you sleep","summary":"Inngest's agent watches SDK pull requests, drafts docs in a sandbox, and opens docs PRs overnight.","source":"hackernews_ai","url":"https://www.inngest.com/blog/docsferatu-an-agent-that-drafts-docs-prs-while-you-sleep","published":"2026-11-01T00:23:44Z"},{"title":"Show HN: Devloops – Adversarial agent loops so humans only make the key decision","summary":"Producer, worker and gatekeeper loops let a coding agent do routine work and escalate only the key decision to a human.","source":"hackernews_ai","url":"https://github.com/fritzprix/devloops","published":"2026-11-01T13:26:51Z"}]},{"name":"Evidence over vibes: benchmarks and tool choice","slug":"evidence-over-vibes","summary":"Today's evals posts argue public scores and framework folklore overstate real-world results.","articles":[{"title":"Is AI Cheap Enough to Replace Developers?","summary":"Claude Opus 4.8 scores 88.6% on SWE-bench Verified but the best public SWE-bench Pro score is 59.1%, and no model clears 47% on the private set.","source":"hackernews_ai","url":"https://zyvop.com/is-ai-actually-cheap-enough-to-replace-developers-8i74u","published":"2026-11-01T08:04:48Z"},{"title":"We tested 12 search APIs for AI agents. Even the best one isn't enough","summary":"Telem.ai tested 12 search APIs for agents; a learned provider mix reached 82.6% with four providers versus 75.5% with two.","source":"hackernews_ai","url":"https://telem.ai/blog/even-the-best-search-provider","published":"2026-11-01T17:57:19Z"},{"title":"The AI cost of JavaScript frameworks","summary":"Nolan Lawson measures the AI cost of JavaScript frameworks instead of relying on claims about speed and productivity.","source":"hackernews_ai","url":"https://nolanlawson.com/2026/10/28/the-ai-cost-of-javascript-frameworks/","published":"2026-11-01T06:06:19Z"}]},{"name":"DeepSeek's open-source coding super-agent","slug":"deepseek-open-source-super-agent","summary":"DeepSeek's harness team open-sourced a router-worker coding agent and its architecture, positioned against Claude Code.","articles":[{"title":"DeepSeek Open-Sources dsh-superagent, a Router-Worker Coding Agent","summary":"DeepSeek open-sources dsh-superagent, a router-worker coding agent.","source":"search_agent_engineering_news","publisher_name":"MarkTechPost","publisher_domain":"marktechpost.com","url":"https://news.google.com/rss/articles/CBMilgFBVV95cUxOVGVmcmxZdFpKS25HOEFNbnFrZmRkd0ZRVFNjUlNMMEEwQXZ3YjFSTm9nNGU3NGZMeFBQWEhtZUlvQU9Va3UzeDlIZXVMaW5QM0w1YUpscHUtMHVqeDlSTnotOTZLNXNUV09abkc3U0VGZjU0MTlLaWJJdGtEWnhTMFlkQWJuWWFVUmRnTFB4eXlUbDNiY0HSAZYBQVVfeXFMTlRlZnJsWXRaSktuRzhBTW5xa2ZkZHdGUVRTY1JTTDBBMEF2d2IxUk5vZzRlNzRmTHhQUFhIbWVJb0FPVWt1M3g5SGV1TGluUDNMNWFKbHB1LTB1ang5Uk56LTk2SzVzVFdPWm5HN1NFRmY1NDE5S2liSXRrRFp4UzBZZEFibllhVVJkZ0xQeHl5VGwzYmNB?oc=5","published":"2026-11-01T07:47:17Z"},{"title":"DeepSeek Open Sources the Architecture Behind Its Super-Agent","summary":"DeepSeek also published the architecture behind the super-agent, not just the prototype.","source":"search_cn_open_weight_labs","publisher_name":"Startup Fortune","publisher_domain":"startupfortune.com","url":"https://news.google.com/rss/articles/CBMikwFBVV95cUxPTFhOWk9yYkRyNkE0d3FxeWNtVDdmcGFNTHBxeWxINk1iUGJMQTd4c2lXRkNMY3NjejVyTGIwZmdYQXUweTdNUHAwblI5M2dGNmd5TWR5SXo4Rmx6d3ZCWjZhX21YZHNoMDNhT3cycEtxd2FGeEdPbkR3UWRiRkNwbTJyandOcEtQXzRyUkxhdlhybTg?oc=5","published":"2026-11-01T00:18:27Z"},{"title":"QwenPU: An LLM running inside another LLM's weights","summary":"QwenPU compiles a 32-bit RISC-V CPU and vector unit into Qwen3.5-4B's weights, running a small network inside the forward pass.","source":"hackernews_ai","url":"https://huggingface.co/divagr1925/QwenPU","published":"2026-11-01T10:15:39Z"},{"title":"An inference server for AMD GPUs, in C++ and HIP","summary":"Open C++/HIP inference server for AMD GPUs with an OpenAI-compatible HTTP API covering chat, Responses, images, audio and video.","source":"hackernews_ai","url":"https://codeberg.org/StillDeadcode/radiance","published":"2026-11-01T19:37:33Z"}]}],"video":{"youtube_id":"gQo0PrumJrg","title":"LLM Digest Daily Explainer: Nov 1, 2026","duration_s":118}}