Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

We're training natural language models to reason by emulating reasoning in natural language, so it's very on brand.


It's on the brand of stuff that works. Expert systems and formal symbolic if-else, rules based reasoning was tried, it failed. Real life is messy and fat-tailed.


And yet we give agents deterministic tools to use rather than tell them to compute everything in model!


Yes, and here they also operate deterministic GUI tools. Thing is, many GUI programs are not designed so well. Their best interface and the only interface they were tested and designed for is the visual one.




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

Search: