HackerTrans
TopNewTrendsCommentsPastAskShowJobs

solomatov

1,563 karmajoined 13 tahun yang lalu

comments

solomatov
·kemarin dulu·discuss
Thanks for sharing.
solomatov
·kemarin dulu·discuss
Super impressive! Is it possible for you to share your methodology of using LLMs?
solomatov
·8 hari yang lalu·discuss
I tried a similar approach before, but it didn't work for me. I didn't get a lot of speedup if any from it. IMO, to get productivity you need some kind of YOLO mode (in a sandbox).

IMO, the goal should be to outsource as much work to the model, as possible, while minimizing effort required to understand and review what is did. For example: ask the model to find out why a bug happens, figure out proof of concept for thing X, incrementally optimize something, do a well specified refactoring with some guide, and similar things.

IMO, what people say about creating loops is a very similar thing. You maximize the work done by the model, while minimizing the amount you need to do to control it.
solomatov
·14 hari yang lalu·discuss
Did they mention the license?
solomatov
·bulan lalu·discuss
> that he doesn't really understand how inference works from a technical perspective

Could you share what tells about it? I.e. where he was wrong about it?
solomatov
·bulan lalu·discuss
> progress was slowing

Do you think it's not slowing? Do I miss anything really important?

My understanding is that we have now is incremental improvement on thinking models which appeared more than a year ago. Of course, a breakthrough might happen, but I don't see one yet.
solomatov
·bulan lalu·discuss
Hopefully we will have more information about these companies when Anthropic IPO filing become public. There's too much speculation without them.
solomatov
·bulan lalu·discuss
Personally, I thought about it as next gen vscode
solomatov
·bulan lalu·discuss
So, it's not open source?
solomatov
·bulan lalu·discuss
> but there is so much evidence to point to this not happening

Could you explain this?
solomatov
·bulan lalu·discuss
>For coding you always want to go with the best model in the category, not something that would be the best model if we went 1 year back which GLM 5.1 is, and I'm saying that as a big fan of GLM cause I run a translation site where GLM is good enough for the price.

Currently, the difference is substantial, but what happens if capabilities saturate?
solomatov
·2 bulan yang lalu·discuss
How central is it in the discrete geometry? Could anyone with the knowledge in the field reply?
solomatov
·2 bulan yang lalu·discuss
Could you share links about this? When it turned into a different interpretation?
solomatov
·2 bulan yang lalu·discuss
It would have been better if they provided not just weights, but also some frontend where it is usable as is.
solomatov
·3 bulan yang lalu·discuss
>but I have seen the local 122b model do smarter more correct things based on docs than opus

Could you please share more about this
solomatov
·3 bulan yang lalu·discuss
Just curious, the fixes are not about weights but about templates, am I right?
solomatov
·3 bulan yang lalu·discuss
Did anyone try it and Gemma 4? Does it feel that it's better than Gemma 4?
solomatov
·3 bulan yang lalu·discuss
I mean not how to do it, it's not that hard, but how to be productive with it.
solomatov
·3 bulan yang lalu·discuss
Does anyone has any tips for starting with Gastown? I am comfortable with couple of agents running, but not yet comfortable with what Gastown offers.
solomatov
·3 bulan yang lalu·discuss
>I’m not sure what you mean by keep it in your head?

If the project I work on is large enough, it takes me some time to get everything I need to understand for review into the short term memory. If it's small enough, it's less of a problem for me.