HackerTrans
TopNewTrendsCommentsPastAskShowJobs

MattPerry

12 karmajoined 6 tahun yang lalu
I hardly build things.

comments

MattPerry
·6 jam yang lalu·discuss
The first picture "gpu rig", "laptop", "server", "cloud node, etc made me realize how little compute I have. I don't have a laptop with 24GB VRAM or a workstation with 96GB. I think if I convinced all of my friends to run LLMs on their gaming PCs, I don't I would have the total VRAM in the picture.

As an aside, I saw this post mentions a public mesh, but I couldn't find any more information.
MattPerry
·kemarin·discuss
I loaded this in a new tab on FireFox and continued to scroll HN. I was so confused on why my computer froze.
MattPerry
·28 hari yang lalu·discuss
Exact same experience. My background is embedded and VLSI so I hedge my bets by saying that LLM are ok for Python scripting, but not there yet for synthesizable Verilog. It is really hard to see if the "how are you using LLMs?" question is for "we are AI Native™" or a form of cheating (like in university).