HackerTrans
トップ新着トレンドコメント過去質問紹介求人

callmekit

no profile record

投稿

TorchFix 0.6.0 – a linter for PyTorch-using code with autofix support

pypi.org
1 ポイント·投稿者 callmekit·2 年前·0 コメント

TorchFix – a linter for PyTorch-using code with autofix support

github.com
2 ポイント·投稿者 callmekit·2 年前·0 コメント

Ask HN: Why there are no large scale programs to synthesize a cell?

1 ポイント·投稿者 callmekit·4 年前·5 コメント

コメント

callmekit
·3 年前·議論
I don't see which model generated each request, where exactly do you see this?
callmekit
·3 年前·議論
So yesterday we had a post (https://news.ycombinator.com/item?id=35200267) that you need a special "play as a grandmaster" prompt to reduce the number of illegal moves for GPT3.5, and that "GPT4 sucks" at chess completely compared to GPT3.5.

Now we have this post that GPT4 plays good and doesn't make illegal moves at all. What changed? What was the prompt? Is it just random noise?
callmekit
·4 年前·議論
What's controversial about Sim City?
callmekit
·4 年前·議論
Thanks, but on the first glance this doesn't seem to be about bottom-up approach of synthesizing a cell from amino-acids, but about modifying existing cells.
callmekit
·4 年前·議論
What exactly are you referring to on that page?
callmekit
·4 年前·議論
Technically it's not ToS to GPU, it's a license to the software: https://www.nvidia.com/en-us/drivers/geforce-license/ So using a completely open source or third party driver and no CUDA is fine.
callmekit
·4 年前·議論
The customer use license specifically talks about datacenters, not "cloud": "The SOFTWARE is not licensed for datacenter deployment, except that blockchain processing in a datacenter is permitted" https://www.nvidia.com/en-us/drivers/geforce-license/
callmekit
·4 年前·議論
There were numerous issues. First one (somewhat mitigated lately) was extremely large number of actions per minute and (most importantly) extremely fast reaction speed.

Another big issue is that the bot communicated with the game via a custom API, not a via images and clicks. Details of this API are unknown - like how invisible units were handled, but it was much higher level than a human would have (pixels).

If you look at the games, the bot wasn't clever (which was a hope), just fast and precise. And some people far from the top were able to beat it convincingly.

And now the project is gone, even before people had a chance to really play against the bot and find more weaknesses.
callmekit
·4 年前·議論
I bought Oculus Quest 2 about a month ago. The games I play the most probably wouldn't be even possible (or at least fun) without VR - Pistol Whip (you need to evade slow-moving bullets) and Thrill of the Fight (boxing simulator). It's more of a fitness device for me now.
callmekit
·5 年前·議論
Does Copilot use other files open in the editor? Are they becoming a part of the prompt?
callmekit
·5 年前·議論
The exact answers to leetcode questions are probably included many times in the Copilot dataset, in many programming languages. Fresh Advent of code problems are much more interesting.
callmekit
·5 年前·議論
That's already mentioned in the blog post: the author first wrote a solution in a normal way, and only then decided to try copilot.
callmekit
·5 年前·議論
I think you need to actually get the new data from Github and finetune the model. Maybe it's done very frequently, but unlikely.
callmekit
·5 年前·議論
I would think the today's code is not a part of the Copilot yet...
callmekit
·5 年前·議論
Do you know how previously unseen numbers in the prompt are encoded, probably the same way? Then GPT3 can not do any math at all, unless the specific numbers were seen before?