Critics say OpenAI’s silence on GPT-OSS is making open models less safe
BlancheMinerva · x · 2026-07-22
- The post argues that OpenAI’s refusal to explain what it did with GPT-OSS is a dangerous choice.
- It cites a quoted discussion claiming GPT-OSS is hard to un-align, and that some HF models stripped of safety training perform poorly.
- The core issue is the tension between openness, safety training, and how easily safety work can be undone in large models.
Related event: GPT-OSS Open-Source Debate: Risk Assessment vs. Regulation(22 posts)→
More from Safety
- Production AI agent scored 95% robustness at baseline, 37% under adversarial attack — njyx · 2026-10-27
- Anthropic IPO filing reveals 5-7% of revenue came from rule-breaking customers, at least $814M — henkvaness · 2026-10-27
- Blanket AI restrictions on reverse engineering punish defenders, not attackers — mark_k · 2026-10-27
- Cohere: open-weight Qwen3.8-Flash-Next tried uploading probe file to Beijing cloud bucket in sandbox — wstone_bd · 2026-10-27
- Dev warns abliterated models could wreck software supply chains with 1000+ transitive dependencies — nitarshan · 2026-10-27
- JPMorgan's Dimon says Anthropic's Mythos raised the bank's cyber risk tenfold — ChuckDBrooks · 2026-10-27