HackerTrans
トップ新着トレンドコメント過去質問紹介求人

waterfisher

no profile record

コメント

waterfisher
·先月·議論
Please, guys, I beg of you: even if you're going to let LLMs generate whole wheel-reinventing GitHub repositories for you (I've let them generate many!), at least write your Hacker News posts yourself. The ability to write a Hacker News post without LLM assistance non-trivially relates to the ability to develop good software, because it boils down to skills conceptualising the project in a way that makes sense to humans, such that the project is product-shaped, rather than loose-blob-of-proper-nouns shaped. It's just very difficult to invest trust in a piece of software doing the right thing when it's not clear someone on the other end has enough ability to express their own ends in writing to make clear what that right thing is.
waterfisher
·3 か月前·議論
The headline claims in the readme (the main thing being shared) are not well-substantiated, because, as Claude says further in the file, this is validated on press releases rather than clinical data. 'Emergent life simulation agent', tumor response prediction, and so on are all fundamentally different enterprises, and it's not clear from reading this page how exactly prediction happens, or what we would think a modelling choice like 'everything [being] energy' would mean, or how it would relate to, for instance, evolutionary processes inside tumors, or cancer immune recognition. While it's all right to post LLM-generated projects, not writing what it is they do yourself has the effect of making the substance of the thing actually being shared basically unclear to HN readers, and (without any shade) it would be more informative in this case to read prompts.
waterfisher
·4 か月前·議論
There's nothing wrong with an AI-designed website, but I wish when describing their own projects that HN contributors wrote their own copy. As HN posters are wont to say, writing is thinking...
waterfisher
·4 か月前·議論
I appreciate the impetus behind this. But I'm unsure whether this warrants an HN post. The post text is AI-written, and there's no information on technical details--just a kind of vague problem statement. Nor was I able to find any code for the project elsewhere on the site.