TGViewer
All about AI, Web 3.0, BCI All about AI, Web 3.0, BCI @alwebbci · 3.89K subscribers
Post #4502 332
Can an LM, starting from random init, learn to generate all of its pretraining data?

Meet Self-Play Pretraining with Zero Data.

Two models start from random initialization: a generator proposes programs for a universal Turing machine and a learner trains on their outputs.

GitHub.
Open in Telegram All posts from @alwebbci
More from @alwebbci
  1. Sep 28, 2026Anthropic launched Claude Sonnet 5.5 30% faster and costs up to 30% less than Sonnet 5 for…
  2. Sep 28, 2026Nvidia introduced Open Agent Safety Platform, bringing together OpenShell and Sentry. Open…
  3. Sep 25, 2026New From DeepSeek: a sandbox platform running 3 million AI agent environments per day. Dee…
  4. Sep 25, 2026Super interesting paper from Google and colleagues. It studies where it's possible to dist…
  5. Sep 24, 2026DeepMind Institute presented 3 new essays: 1. How can we control misbehaviour in agent swa…
  6. Sep 24, 2026Stanford introduced Matryoshka Attribution, a new attribution method which uses gradient d…
Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →