Hacker Newsnew | past | comments | ask | show | jobs | submit | hanneshdc's commentslogin

Agreed on integrals, but the derivative is relatively simple?

If f(x) = exp(x) - ln(x) then f’(x) = exp(x) - 1/x, which is representable in eml form as well.

To the overall point though, I don’t think it helps make derivatives easier though. To refactor a function to eml’s is far more work than refactoring into something that’s trivially differentiable with the product rule and chain rule.


You mean

  f'(x) = eml(x,x) + eml(1,eml(eml(1,x)),1) + eml(eml(1, exp(eml(1, 1))),-eml(1, eml(eml(1, x))),1)
and I still have to macroexpand a few

  x-y = eml(eml(1, exp(eml(1, x))), eml(y,1)) 
but I got really bored

Yes - and this also gives me hope that the (very valid) issues raised by this paper can be mitigated by using models without KPIs to watch over the models that do.


But how would you evaluate performance of those watching models? It'd need an indicator, hopefully only one that's key to ensure maximal ethic compliance.


> This attack stems from the combination of two design flaws: overprivileged database access (service_role) and blind trust in user-submitted content.

No, there is only one design flaw, the overprivileged database access. An LLM shouldn't be given more access than the user who is interacting with the LLM has.


Consider applying for YC's Summer 2026 batch! Applications are open till May 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: