A 10,000-agent swarm solved NS — a single Codex agent is not the same thing
daniel_mac8 · x · 2026-11-18
Daniel Mac points out that the recent NS-solving result was achieved by 10,000 agents working as a swarm, not by a single agent — so running one agent in Codex is not equivalent to that feat. A useful clarification on the scale conditions behind multi-agent results.
More from coding & agent
- Auto-approving PRs: Qodo's rules-based workflow handles the coding-agent PR bottleneck — omarsar0 · 2026-11-18
- Record your judgment process 3 times, let AI build business evals from it — alliekmiller · 2026-11-18
- HF releases RL-trained Qwen3.8 adapter for opencode: +16pts on SWE-bench Pro, 8x fewer tokens — LysandreJik · 2026-11-18
- Noodle: Free open-source Mac app runs collaborative personal AI agents locally — Dave_Maynor · 2026-11-18
- Top engineers have stopped reading code: specs and tests become the persistent artifact — ZeeshanZiaML · 2026-11-18
- Doing EQ/compression on voiceovers with FFmpeg inside Antigravity — alexanderchen · 2026-11-18