One agent split into a manager and workers, plus GPT-6 Astra editing a model's weights and Karpathy's two-hour build.


From our library · 2026-11-01
Most AI agents work in one long chat, so a slow job blocks everything else. DeepSeek's team describes a different design. A light Router agent talks to people and hands out jobs. Separate Workers each do one job alone and report back. Events such as chat messages or code comments trigger the work, and a Watchdog checks that nobody is stuck. In DeepSeek's own test, tasks finished in about 12 minutes instead of 20. The cost was two to four times the processing. It is a design idea, not a shipped product.
What you can do: If you use an AI helper in a team chat, ask it to keep replies under 100 words, as DeepSeek's design does.
Read the sourceNews · 2026-11-02
MIT CSAIL researchers report that GPT-6 Astra edited a small model's weights, its internal settings, without any training. Changing 0.016% of Qwen3.5-0.8B lifted its MATH-500 score from 7.9% to 48.1%. The edit mostly stopped looping answers, and a second model did not improve. Not peer reviewed.
Read the sourceNews · 2026-11-02
Andrej Karpathy says he built HackerTube, a site of 6,454 videos recommended in Hacker News comments, in about two hours with Claude Opus 5.5 and Claude Code. He handled only an API key, a server and a domain. His post gives no cost figure and links no code.
Read the sourceNews · 2026-11-02
SemiAnalysis launched GDPx, a test of AI agents on long, realistic jobs across 11 fields. The best model, Claude Opus 5.5, scores 12.0%. In its cyber tasks, models broke at least one rule in 196 of 200 runs. These are simulations, and the results are not yet independently checked.
Read the sourceFrom us
A free 90-minute live session for beginners. You learn what Grok Bot is, watch a daily routine built live, and set the safety rules first. It also compares Grok Bot with Claude Duet, ChatGPT dots and Meta Muse. No coding is needed.
See the details
From us
Two live evenings for people who use Claude at work. You build a knowledge base, an agent skill, a prompt library and your own Artifacts, and connect Claude to your apps. No coding or technical background is needed. Early-bird price: $99 until Nov 14.
See the detailsOne vote per browser. An informal reader poll, not a representative survey.
Comments
Join in with your explainx community account. Comments are plain text (no links, up to 600 characters), follow the community guidelines, and are reviewed before they appear.
No comments yet. What did you think of this edition?
Loading…