AINews · Editorial
Weight Space Programming - LLMs can natively read & write neural network weights
The November 2 AINews Markdown covers October 31 through November 2. Its lead follows a weight edit that helped a small Qwen model finish math problems where it had previously exhausted its token budget.
Read the issue on GitHub ↗Stories from this issue
Ranked by reader votes, with editorial order breaking ties. Markdown committed . Added to the archive 2026-11-03.
DeepSeek releases a prototype that routes work to isolated coding agents (x.com/deepseekharness)
A persistent router talks to the user and delegates tasks to workers triggered by GitHub events. DeepSeek reports a fall in p95 completion time from 29.5 to 15.7 minutes in an internal comparison.
▲ Upvote0 points· DiscussKarpathy mines Hacker News comments for recommended videos (x.com/karpathy)
HackerTube used twenty years of Hacker News discussions to identify 6,454 videos that commenters repeatedly recommended. Karpathy describes building and deploying the site with Claude Code in roughly two hours.
▲ Upvote0 points· DiscussMiniMax highlights local serving options for its 428B Flash model (x.com/minimax_ai)
Community implementations of M3.1 Flash include a two-bit GGUF at 143.9 GB and an AMD Instinct quantization recipe. The roundup also describes offloading experts across four RTX 3090s.
▲ Upvote0 points· DiscussDavid Fowler uses cloud coding agents to open around 90 ASP.NET Core performance PRs (x.com/davidfowl)
Fowler reports spending about $230 in tokens over a day with GitHub’s cloud agents and Opus 5.5. The reported count measures proposed pull requests.
▲ Upvote0 points· DiscussLlamaIndex adds a higher-effort document extraction mode (x.com/jerryjliu0)
LlamaIndex reports that its Extract Max Effort mode surpassed Astra and Opus at their highest reasoning settings on its document-extraction evaluation, at a lower cost.
▲ Upvote0 points· Discuss