Show HN: I RL-trained an agent that trains models with RL (for –$1.3k)

Re:Show HN: I RL-trained an agent that trains models with RL... by Danau5tin on Tuesday July 14, 2026 @09:56AM (#48906961)

Yes I'd heard the labs (Anthropic mostly) speaking about LLMs training LLMs, so I wanted to make things a little more concrete and test it out myself! Essentially you are correct though, my framework allows the agent access to compute, but also the agent itself is being trained to become better at training models with that compute.

[ Parent | on HN ]

Re:Show HN: I RL-trained an agent that trains models with RL... by vorticalbox on Tuesday July 14, 2026 @12:58PM (#48909796)

i remeber reading in one of the release blog posts that that version was the "first that codex helped train"

[ Parent | on HN ]

Re:Show HN: I RL-trained an agent that trains models with RL... by Danau5tin on Tuesday July 14, 2026 @01:00PM (#48909828)

Yes exactly, and also there is auto-research by Karpathy, Fable-5 on parameter golf etc which point to the direction of highly-assisted / autonomous AI training as the future. Wild.

[ Parent | on HN ]