Most popular guardrail-removal library was written by Claude, researcher says
BlancheMinerva · x · 2026-09-30
Researcher Blanche Minerva says the most popular library for AI safeguard removal was built by Claude — a view Anthropic reportedly disagrees with. The context: Pliny's OBLITERATUS abliteration framework (8k+ GitHub stars) was built with Anthropic's own models, timed against Anthropic's IPO and its blog post calling an open-weight competitor dangerous. She also cites hackers using Claude and ChatGPT to attack Mexican government organizations from December to February, with suspected ransomware involvement.
More from Fun
- "Can't two bros just do a photoshoot?" AI community still probing that viral photo — tekbog · 2026-09-30
- 'AGI will book your flights': VC pitch criticized for shrinking AGI to errands — tekbog · 2026-09-30
- "The planet wants mathematicians more than frontier models" mocked as peak detachment — RexDouglass · 2026-09-30
- 'Most People Just Want Slop': Techies Keep Misreading What Normies Want From AI — max_paperclips · 2026-09-30
- Filmmakers jam with AI video generation wait times to shoot a music duet with Luma — mrjonfinger · 2026-09-30
- Musk jokes the best AI sandbox is a Delta flight — no internet access at all — elonmusk · 2026-09-30