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

Research takes some time, both to do but also to publish. In my area (programming languages), we have 4 major conferences a year, each with like a 6-to-8-month lag-time between submission and publication, assuming the submission is accepted by a double-blind peer review process.

I don't work in this area (I have a very unfavorable view of LLMs broadly), but I have colleagues who are working on various aspects of what you ask about, e.g., developing testing frameworks to help ensure output is valid or having the LLMs generate easily-checkable tests for their own generated code, developing alternate means of constraining output (think of, like, a special kind of type system), using LLMs in a way similar to program synthesis, etc. If there is fruit to be borne from this, I would expect to start seeing more publications about it at high-profile venues in the next year or two (or next week, which is when ICFP and SPLASH and their colocated workshops will convene this year, but I haven't seen the publications list to know if there's anything LLM-related yet).



ICFP and SPLASH are this week, actually! Here's the program website for anyone interested: https://conf.researchr.org/program/icfp-splash-2025/program-...

(I have a pretty unfavorable view of LLMs myself, but) a quick search for "LLM" does find four sessions of the colocated LMPL workshop that are explicitly about LLMs and AI agents, plus a spread of other work across the schedule. ("LMPL" stands for "Language Models and Programming Languages", so I guess that's no surprise.)


Well, I did post my comment last week when "next week" was accurate. ;) But thanks for linking the program!


Oh! The thread must have been boosted on a resubmission, or something, because for me it shows your comment as having only been posted yesterday D:





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

Search: