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.
Read in the app — free, in 9 languages
Related stories
Meta's assistant keeps an hourly file on everyone in your life.2026-10-05Two senators want prison time for bosses whose AI agents hack.
2026-10-05One command restores the Apple Intelligence off switch Apple deleted.
2026-10-05OpenAI will ship a Codex upgrade daily for 28 days or reset limits.
2026-10-05Untuned models solved agent tasks their polished versions could not.
2026-10-04