News for hackers. Stuff that matters.
Re:Anthropic IPO by 72deluxe on Thursday November 12, 2026 @10:46AM (#50469319)
That just means the business automation is not deterministic, and highlights the issue with LLMs. The solution is not to switch providers but instead make the LLMs generate something that is deterministic given the same input.
Re:Anthropic IPO by disgruntledphd2 on Thursday November 12, 2026 @11:06AM (#50469648)
> That just means the business automation is not deterministic, and highlights the issue with LLMs. The solution is not to switch providers but instead make the LLMs generate something that is deterministic given the same input.

I'm thinking of stuff that would typically be outsourced (like compliance stuff for identity verification et al), where it's really really hard to have deterministic rules.

LLMs are definitely a step up in dealing with fuzzy inputs, and enables you to mostly automate stuff that really wasn't feasible before.

But you do need really good evals and monitoring to make this work effectively.

Re:Anthropic IPO by 72deluxe on Thursday November 12, 2026 @11:29AM (#50469997)
Ah that would make sense then. I was thinking strictly in terms of business logic for handling input of data from an external source; sort of glorified data validation and then a decision based on the input data.
Re:Anthropic IPO by disgruntledphd2 on Thursday November 12, 2026 @04:09PM (#50474312)
You'd be crazy to spend LLM money on that, but its probably happening all over the place.