←
difficultyang3,921 posts
difficultyang avatar

difficultyang

@difficultyang

More social alt of @ezyang

◷ Joined April 2022▧ 463 Photos and videos
difficultyang avatar
difficultyang@difficultyang·31m

Better to use a model that is not too smart and makes mistakes it can keep you on your toes

difficultyang avatar
difficultyang@difficultyang·1h

A benchmark where you take old PL paper results that were pencil and paper only and formalize them

difficultyang avatar
difficultyang@difficultyang·3h

There is also a mode collapse problem, where everyone will use the same models to assist in the formalization, resulting in a monoculture where every implementation may make the same mistakes

difficultyang avatar
difficultyang@difficultyang·3h

Formalization is also an interestingly shaped task where human graders are arguably less good than LLM graders, but now there is a trust bootstrap problem...

difficultyang avatar
difficultyang@difficultyang·4h

As I work on formalization stuff, one of the funniest mode collapses is everyone's AI "independently" finding exactly the same ambiguities/omissions in English specs

difficultyang avatar
difficultyang@difficultyang·Nov 17

In the next year, will model improvements allow humans to substantially automate the process of formulating a TCB for formal verification? Discuss.

difficultyang avatar
difficultyang@difficultyang·Nov 17

Xianxia has a clear solution to this but American gamers are not ready for it

BoTW and ToTK have the same issue: The first 40 hours is the best survival game ever made that forces you to think, be creative, conserve resources and take it all in slowly and then you get too many items/abilities that trivialize much of the rest of it.

difficultyang avatar
difficultyang@difficultyang·Nov 15

It feels like it's good to run agent swarms more slowly (eg less parallelism) because it makes it easier to figure out if you have asked for the wrong thing

difficultyang avatar
difficultyang@difficultyang·Nov 15

Suppose you have a function that takes 10s to run. Seems wrong to optimize a 1ms startup phase. But what if I said that the function SHOULD take 1ms. Then even the startup is 100% of your budget. Everything must be worked on! The power of expectations.

difficultyang avatar
difficultyang@difficultyang·Nov 15

NVIDIA doesn't publish info about SASS but the community figured out that nvdisasm has a domain specific language that encodes a comprehensive spec about SASS. It tickles me to no end the community calls this "The Rosetta String"