HackerTrans
TopNewTrendsCommentsPastAskShowJobs

smhinsey

no profile record

comments

smhinsey
·5 ay önce·discuss
This is a really interesting approach but I'm curious to see how it translates to the actual mesh extrusion, or whatever 3d technique they adopt. It's relatively easy to do this in 2d, it's the 3d solution that accommodates terrain variation that introduces the real explosion of complexity
smhinsey
·6 ay önce·discuss
This gets at the heart of the quality of results issues a lot of people are talking about elsewhere here. Right now, if you treat them as a system where you can tell it what you want and it will do it for you, you're building a sandcastle. Instead of that, also describe the correct data structures and appropriate algorithms to use against them, as well as the particulars of how you want the problem solved, it's a different situation altogether. Like most systems, the quality of output is in some way determined by the quality of input.

There is a strange insistence on not helping the LLM arrive at the best outcome in the subtext to this question a lot of times. I feel like we are living through the John Henry legend in real time
smhinsey
·8 ay önce·discuss
For Unity, claude is capable of creating .meta files and editing .unity scenes, at least until they get really large
smhinsey
·geçen yıl·discuss
Fundamentally, they are really powerful text transformers with some additional capability. The further away from that sweet spot and the closer to anthropomorphization the more unreliable the output
smhinsey
·geçen yıl·discuss
It seems like the emphasis on getting results in one shot reduces the maximum potential quality of the output as compared to a more incremental approach. For example, create an initial prompt to generate a structured description of the features in the program you've described. You can then iterate on this and follow up with a prompt that generates a structured description of a system architecture based on the feature description, and iterate on that. You could build up other informational layers as well, before aggregating all that structural data into the generation of the actual code. This can feed into the generation of tests as well.

If you look at things like LLM party for comfyui, it's the same basic concept.