HackerTrans
TopNewTrendsCommentsPastAskShowJobs

juggy69

32 karmajoined 6 years ago

Submissions

Paranoid LLMs

whyjay.vercel.app
1 points·by juggy69·2 days ago·0 comments

Ask HN: Attempts to solve ARC-AGI-3

arcprize.org
2 points·by juggy69·6 months ago·1 comments

comments

juggy69
·3 months ago·discuss
I can't figure out how to install this. After doing ./build.sh what do I do next??
juggy69
·5 months ago·discuss
Do you mean that sitting with the problem for days is a weakness that you should fix since you're wasting time making no progress? Or that it is a necessary practice in order to understand your weaknesses?
juggy69
·6 months ago·discuss
ARC-AGI-3 is the latest benchmark from Arc Prize. It has an interesting departure in that each puzzle is now interactive, like a mini RL task. Players are not told the goal, requiring the agent to explore and model the puzzle to solve it.

Is anyone giving this an attempt? May or may not be LLM-powered. Would love to hear your approaches.
juggy69
·6 months ago·discuss
Here i was thinking of transformer architecture
juggy69
·6 months ago·discuss
Is there value in using deep RL for problems that seem more suited to planning-based approaches?
juggy69
·7 months ago·discuss
Have to agree that is sounds GPT-generated. Why so many colons? And the incurable marketing-speak.