nikkindev
Re:If you love a website, back it up
on Tuesday November 03, 2026 @04:09AM (#50349718)
I have been using HTTrack is cases where I want a browsable local version of any site (not just a page)! Most of the applications mentioned here as comments only allow for saving a single page. But afaik, only HTTrack allowed me to save a local version of the website and not just a webpage. The “depth” argument allows me to do that when downloading a site through CLI
Re:Using uv as your shebang line
on Tuesday January 28, 2025 @01:45PM (#42856213)
“Lazy self-installing Python scripts with uv”[1] article from Trey Hunner has more details with examples
[1] https://treyhunner.com/2024/12/lazy-self-installing-python-s...
Re:Entropy of a Large Language Model output
on Tuesday January 14, 2025 @02:54AM (#42694826)
Author here: Wholeheartedly agree with your comment on hallucination. I initially set out to answer the question “Will entropy help identify hallucination?” And soon realised that it doesn’t, for the same reasons you mentioned above. So I pivoted to just writing about the entropy measure in the post. And this is also reflected by how I started with hallucination and then quickly veered away from it. I’ll be more careful in future posts & conversations. Thanks!
Re:Entropy of a Large Language Model output
on Monday January 13, 2025 @01:52PM (#42687072)
Author here: Thanks for the explanation. Intuitively it does make sense that anything done during "post-training" (RLHF in our case) to make the model adhere to certain (set of) characteristics would bring the entropy down.
It is indeed alarming that the future 'base' models would start with more flattened logits as the de-facto. I personally believe that once this enshittification is recognised widely (could already be the case, but not recognized) then the training data being more "original" will become more important. And the cycle repeats! Or I wonder if there is a better post-training method that would still withhold the "creativity"?
Thanks for the RLHF explanation in terms of BPE. Definitely easier to grasp the concept this way!
Re:Entropy of a Large Language Model output
on Monday January 13, 2025 @01:21PM (#42686654)
Author here: Really interesting work. Updated original post to include link to the paper. Thanks!
Re:Entropy of a Large Language Model output
on Monday January 13, 2025 @01:08PM (#42686430)
Author here: Yes. You are right. I was meaning to paint a picture that instead of the next token appearing magically, it is sampled from a probability distribution. The notion of determinism could be explained differently. Thanks for pointing it out!
Re:Show HN: I built Wuf, mobile notifications for all your needs
on Tuesday September 12, 2023 @09:43AM (#37481132)
Not for self hosting. Self hosting [1] is still free since the code is open source.