TGViewer
All about AI, Web 3.0, BCI All about AI, Web 3.0, BCI @alwebbci · 3.9K subscribers
Post #4532 163
Stanford introduced DeLM, a decentralized approach to multi-agent systems.

DeLM improves accuracy by up to 17.5 percent points and runs up to 2.49× faster than the Codex and Claude Code harnesses on long-horizon tasks from Terminal-Bench 4.0, DeepSWE v1.1, and ProgramBench.

How it works:

the main agent is replaced by a shared context and a task queue. Agents claim tasks asynchronously and build on or correct each other’s progress, and every agent’s status is visible to the others.

You can run DeLM’s collaborating agents directly in Codex and Claude Code
yuzhenmao.github.io Decentralized Multi-Agent Systems with Shared Context DeLM replaces the main agent with a shared context and a task queue. More accurate and faster than Codex, Claude Code, their native subagents, and AOrchestra.
Open in Telegram All posts from @alwebbci
More from @alwebbci
  1. Oct 9, 2026Google researchers built an AI that reads a problem, forms hypotheses, runs experiments, w…
  2. Oct 8, 2026Robot world models now have scaling laws. Meta trained an 8B-parameter JEPA on 15,000 hour…
  3. Oct 8, 2026Last week some of South Korea's biggest banks were hit by a cyberattack. Thanks to a repor…
  4. Oct 8, 2026Google and Unity launched Playground ( experimental) , a browser-based tool where you can…
  5. Oct 7, 2026Anthropic released Claude Haiku 5.5: the cheapest, fastest, and most capable small model O…
  6. Oct 7, 2026Sui partners with Alibaba Cloud to enable stablecoin-based per-call payments for AI agent…
Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →