Lack of training transparency hampers safety research; synthetic data issues often skill-based
JacquesThibs · x · 2026-08-21
JacquesThibs notes that the lack of transparency regarding AI labs' exact training processes hinders external safety efforts. It is difficult to determine if safety experiments are attacking strawman setups. He cites the claim that "synthetic data destroys models" as an example of a problem that is mostly a skill issue rather than an inherent flaw.
More from Safety
- AI crossing capability thresholds may leave many security systems exposed — austinc3301 · 2026-08-21
- Analysis: AI infrastructure shifts towards secrecy and state control — FinanceYF5 · 2026-08-21
- Cyber researcher: model attackers as real organizations and the AI cyber threat looks overrated — joshua_saxe · 2026-08-21
- MIT Paper Finds Deleting Artist Data Doesn't Stop AI Recreating Images — technollama · 2026-08-21
- Space datacenters won't escape pushback: States will regulate rocket launches — wordgrammer · 2026-08-21
- Nobody measures how long an agent keeps working after you revoke its access — anp2_protocol · 2026-08-21