1. samwho Dec 29, 2025 parent

   I love this, the end result looks so good.

   Something you don’t really mention in the post is why do this? Do you have an end goal or utility in mind for the book shelf? Is it literally just to track ownership? What do you do with that information?

2. samwho Dec 23, 2025 parent

   Thank you <3
3. samwho Dec 19, 2025 parent

   Thank you! <3

   These are all built with React and CSS animations (or the Web Animations API where I needed it). I’m not very good at React so the code is a real mess. 2 of the components also use threejs for the 3D bits.

   For the stuff on my personal site, which simonw graciously linked to in another reply, you can see all the code behind my work at https://github.com/samwho/visualisations

4. samwho Dec 19, 2025 parent

   Simon, you’re too kind. Thank you. <3
5. samwho Dec 19, 2025 parent

   When I was writing this, GPT 5.1 was the latest and it got it right away. It’s the sequence of prime numbers fwiw :)
6. samwho Dec 19, 2025 parent

   How would information leak, though? There’s no difference in the probability distribution the model outputs when caching vs not caching.
7. samwho Dec 19, 2025 parent

   The only thing that comes to mind is some kind of timing attack. Send loads of requests specific to a company you’re trying to spy on and if it comes back cached you know someone has sent that prompt recently. Expensive attack, though, with a large search space.
8. samwho Dec 19, 2025 parent

   I was wondering about this when I was reading around the topic. I can’t personally think of a reason you would need to segregate, though it wouldn’t surprise me if they do for some sort of compliance reasons. I’m not sure though, would love to hear something first-party.
9. samwho Dec 19, 2025 parent

   With KV caching as it’s described there it has to be a prefix match. OpenAI state in their docs they don’t cache anything below 1024 tokens long, and I’m sure I read somewhere that they only cache in 1024 token blocks (so 1024, 2048, 3072, etc) but I can’t find it now.

   There’s been some research into how to cache chunks in the middle, but I don’t think any of the providers are doing it yet because it needs the prompt to be structured in a very specific way.

10. samwho Dec 19, 2025 parent

    Could you tell me what browser/OS/device you’re using? A few people have said this and I haven’t been able to reproduce it.
11. samwho Dec 19, 2025 parent

    Another person had this problem as well and we couldn’t figure out what causes it. We suspect something to do with WebGL support. What browser/device are you using? Does it still break if you disable all extensions? I’d love to fix this.
12. samwho Dec 19, 2025 parent

    It’s funny, I didn’t set out for that to be the case. When I pitched the idea internally, I wanted to scratch my own itch (what on earth is a cached token?) and produce a good post. But then I realised I had to go deeper and deeper to get to my answer and accidentally made a very long explainer.
13. samwho Dec 19, 2025 parent

    Yay, glad I could help! The sampling process is so interesting on its own that I really want to do a piece on it as well.
14. samwho Dec 19, 2025 parent

    Yeah! It’s planned for sure. It won’t be the direct next one, though. I’m taking a detour into another aspect of LLMs first.

    I’m really glad you liked it, and seriously the resources I link at the end are fantastic.

15. samwho Dec 19, 2025 parent

    Huh, when I was writing the article it was GPT-5.1 and I remember it got it no problem.
16. samwho Dec 19, 2025 parent

    Thank you so much <3
17. samwho Dec 19, 2025 parent

    It is the same ngrok!

    The product has grown a lot since the mid 2010s. Still got free localhost tunnelling, but we also have a whole bunch of production-grade API gateway tooling and, as of recently, AI gateway stuff too.

18. samwho Dec 17, 2025 parent

    Thank you so much <3

    Yes, I recently wrote https://github.com/samwho/llmwalk and had a similar experience with cache vs no cache. It’s so impactful.

19. 306 points Dec 16, 2025

    Prompt caching for cheaper LLM tokens

    72 comments samwho ngrok.com
20. 4 points Dec 14, 2025

    Show HN: Llmwalk – explore the answer-space of open LLMs

    0 comments samwho github.com
21. 481 points Dec 12, 2025

    “Are you the one?” is free money

    115 comments samwho owenlacey.dev
22. samwho Nov 24, 2025 parent

    The one where he does a landscape is one of my favourite videos of all time.
23. samwho Oct 22, 2025 parent

    Someone gave me the advice to use animals, ideally animals of very different sizes or colours. People instantly picture them and remember them.
24. 13 points Oct 1, 2025

    Why ports <1024 are privileged and require root

    0 comments samwho utoronto.ca
25. samwho Aug 31, 2025 parent

    This is what I use and I’ve been very happy with it for many years. It hasn’t caused me any trouble and as far as I can tell it hasn’t changed in the whole time I’ve used it.
26. samwho Aug 25, 2025 parent

    Hehe, yes, Ned sent me a lovely email the other day about it. Happy to be doing my part.
27. samwho Aug 25, 2025 parent

    Can’t imagine what it might be.
28. samwho Aug 25, 2025 parent

    I’m not sure that’s quite my position. Happy to cede that I lack fluency, and I appreciate your time and the time others have given to help me understand.
29. samwho Aug 25, 2025 parent

    I did push up a rewording that hopefully lands better. Fingers crossed.

This user hasn’t submitted anything.