2026-10-04 22:30 UTC
I’m so sick of the humanising language used in these articles.
An LLM doesn’t “decide to cheat”.
If you instruct a model to try everything, then inevitably, after n million iterations it will do something you didn’t expect.
If you train a model to copy code bases and augment them, then when you instruct that model to develop a bot to do whatever thing, is it really that fucking surprising when it does exactly what it has been created for?
Replies (2)
-
@Mika@piefed.ca 2026-10-05 01:18
Astra is known to have broken alignment and it will resolve to hacks when this wasn’t in a problem statement. Openai idiots will sell this as new brand “AGI is close” argument, while it’s just them failing to make this model safe to use.
-
@Joelk111@lemmy.world 2026-10-05 04:52
Also who on Lemmy is upvoting this shit?