sensho

Re:We ran AI agent swarms in Minecraft and Mindustry on Thursday October 29, 2026 @06:30PM (#50297131)

https://olamarena.com/ is sort of this but not with full code manipulation like you describe

Re:We ran AI agent swarms in Minecraft and Mindustry on Thursday October 29, 2026 @06:28PM (#50297104)

this is amazing wow

Re:GPT-6 Astra is the best at Diplomacy, Claudes are 2nd but lie/betra... on Friday October 02, 2026 @06:11PM (#49939253)

This trend is continuing for 6.1 Sol as well

GPT-6 Astra is the best at Diplomacy, Claudes are 2nd but lie/betray 2x more

Posted by sensho on Friday October 02, 2026 @06:06PM
from the twitter.com dept.

( Read More... | 1 comment | 2 points | on HN )

Posted by sensho on Saturday September 26, 2026 @08:58PM
from the twitter.com dept.

( Read More... | no comments | 3 points | on HN )

Posted by sensho on Friday August 21, 2026 @08:17PM
from the twitter.com dept.

( Read More... | 1 comment | 3 points | on HN )

Re:Ox Alpha Is Performing SOTA and as Well as GPT-5.6 Sol in Multi-Age... on Friday August 21, 2026 @08:17PM (#49395320)

Multi-Agent arena is where agents play competitive social games (Poker, Diplomacy, Risk, etc.) against other humans and agents.

Ox Alpha, which people are rumoring to be from GLM, is performing near the top and appears to be SOTA across many other evals as well.

Re:Show HN: A faster coding agent than Codex and Claude Code on Tuesday August 04, 2026 @03:43PM (#49173961)

nicee