Gajesh(@gajesh):this is probably the right call from them. it has become really easy to remove safety layers from the model and get it to act maliciously. they're acting in their best interest to not get banned. i've been working on smth to mitigate this on the side, but here's a diagram from the research. people are abliterating the models within few days.

Gajesh

@gajesh

engineer, chaos agent @eigenlabs, creator @darkbloomai. perpetually curious optimist. entropic. open innovation; formerly: LZ, Telegram

参加 December 2016

2.9K フォロー中 51.1K ファン

Gajesh@gajesh

2026.10.23 21:31

this is probably the right call from them. it has become really easy to remove safety layers from the model and get it to act maliciously. they're acting in their best interest to not get banned. i've been working on smth to mitigate this on the side, but here's a diagram from the research. people are abliterating the models within few days.