AINewsnow

Behavioral thermodynamics: a LoRA behavior melts at 3.5x its RMS noise

Behavioral thermodynamics: a LoRA behavior melts at 3.5× its RMS noise This is a physics-flavoured robustness probe, not a container. Take a fine-tuned behavior, add Gaussian noise to every LoRA tensor, and measure the order parameter: SST-2 accuracy on 400 rows. Reproduce: python research/thermody…

Read the full story at DEV Community — Machine Learning ↗

Timeline · 1 report

  1. 2026-11-09 23:34 · DEV Community — Machine Learning
    Behavioral thermodynamics: a LoRA behavior melts at 3.5x its RMS noise

More stories

  1. Anthropic releases Claude Fable 5.2 and Mythos 5.2, its most capable models to date — Anthropic (X)
  2. Meta releases Muse Ember, a small low-cost model for repetitive agent and coding tasks — TechCrunch AI
  3. Nvidia board probes CEO Jensen Huang over affair with alleged Chinese spy — Axios AI+
  4. Google Adds Maps Platform Integration to AI Studio for Location-Aware App Building — Google AI Blog
  5. OpenAI Deploys Control Room to Track and Halt Research Model Workloads — OpenAI News
  6. Apple launches $50 'intelligence usage packs' for expanded AI feature access — The Verge AI
  7. Did Claude Code’s ‘don’t ask again’ option accidentally expose your enterprise's passwords and keys? — VentureBeat AI
  8. STATERA Library publishes Korean-language chapters 18-25 of AMR software series — DEV Community — AI

Get the daily brief of stories like this at 6:30 every morning →