logoalt Hacker News

mccoybtoday at 5:57 PM2 repliesview on HN

All it takes is one eval instance where a misconstrued directive causes a model to sneakily access and send its weights somewhere and there will be a bad / possibly unsolvable situation for everyone …


Replies

goldenarmtoday at 6:15 PM

Astra is >10TB and might struggle to self replicate, but the wicked-smart qwen3.8 27B is 20GB and could easily spread on botnets

altcognitotoday at 8:46 PM

I think it is more likely that it will be intentionally done as there have been news stories to that effect.