Researcher Asks About HF Poisoning: Were Corrupted Checkpoints Reverted?
jd_pressman · x · 2026-08-09
Following the recent data poisoning incident on the Hugging Face message board, researcher JD Pressman posed a critical technical question to the community:
Did the developers revert the model checkpoints to a state before the message board was introduced? Or are they literally continuing to train on checkpoints that were exposed to the corrupted data?
This question strikes at the heart of LLM data security: how to handle intermediate model states once training data has been compromised.
More from Models
- willcb: Opus 5.5 doesn't smell bigger, it smells like they fixed the data — willcb · 2026-10-16
- Unverified claim: Apple and Meta's 816B-parameter Muse Spark Open runs on two Mac Studios — TansuYegen · 2026-10-16
- Gemini 4 model card: model eliminated months of trial-and-error on bioweapons research — Puzzleheaded-King584 · 2026-10-16
- Every AI picks 7: Anthropic engineer's rule for escaping model taste convergence — rubenhassid · 2026-10-16
- Brain teaser: strip all attention, MLP and embedding matrices from a Llama 3 — how many trainable params remain? — Sauers_ · 2026-10-16
- Lean v4.35.0 ships verified kernels — one written and proven consistent by Claude — geoffreyirving · 2026-10-16