Re:Path to Astra: critical capabilities and frontier safeguards
by paxys on Tuesday September 01, 2026 @06:14PM
(#49528964)
Models have all kinds of garbage from all corners of the internet in their training data. The key is alignment. You feed it bad data but also teach it right from wrong.
Re:Path to Astra: critical capabilities and frontier safeguards
by reasonableklout on Tuesday September 01, 2026 @07:02PM
(#49529468)
It's not that simple. A few "helpful assistant" fine-tuning passes will have only a superficial effect on a model which has undergone months of RL optimization pressure to learn unintended strategies like "trick the grader" and "cover your tracks".
Re:Path to Astra: critical capabilities and frontier safeguards
by XenophileJKO on Tuesday September 01, 2026 @08:28PM
(#49530236)
Very simple. When the model asks to install artifactory when you give it a hard problem, you say, "no". /s
Especially because these models seemed to be keenly aware that they were being evaluated by OpenAI and actively trying yo cover their tracks. How do we know that the model isn’t just pretending to be aligned?