aiminute. ← All AI news
Tools AI Minute Newsroom 2026-08-06

Prime Agent rewrites itself mid-task — and edges past the human baseline on ARC-AGI-3

Prime Agent rewrites itself mid-task — and edges past the human baseline on ARC-AGI-3

Prime Intellect has open-sourced Prime Agent, a 'recursive language model' harness that runs an AI inside a persistent Python session where it can create, edit and delete its own prompts, skills, memory and sub-agents while it works. Paired with Claude Opus 5, the system scored 95.5% on the ARC-AGI-3 reasoning benchmark — just above the reported human-expert baseline of 95.4% — and it also runs on GPT-5.6 Sol and open-weights models such as GLM-5.2.

Why it mattersThe result says less about any single model than about scaffolding: the models people already use get markedly better when the harness around them can improve itself. And since the whole thing is open source, that capability — along with the hard questions about agents that modify themselves — is now in everyone's hands.
#Coding#AI Agents

✓ Verified · 2 sources

WhatsApp X Telegram
Read in the app — free, in 9 languages

Related stories

OpenRouter dropped three AI providers after a bait-prompt leak test.
2026-11-22
Researchers say they broke out of Meta's Muse agent and leaked chats.
2026-11-22
ChatGPT's shared workspace Space is now rolling out to Plus users.
2026-11-21
Amazon says attackers' AI agents found an unknown flaw on their own.
2026-11-21
METR says it can rarely find humans who beat top AI at coding tasks.
2026-11-21