Live data from Hacker News

Viewing profile — supriyo-biswas

supriyo-biswas

HN member
Joined
Sat, Dec 10, 2022, 2:55 AM UTC
HN karma
5,343
Public activity
1,506 items

About supriyo-biswas

Opinions expressed are in a personal capacity and not supported or shared by my past or current employer(s).

Email: raptors_03pout@icloud.com

Recent public activity

  1. comment
    Comment #49218354

    Is it really that complicated? I personally use direnv with nix to have per-project dependency versions installed automatically, and I’ve never had too much trouble. I know that th…

  2. comment
  3. comment
    Comment #49165235

    I mean we've had Matt Mullenweg from Wordpress make various below-the-belt comments about their competitors and other companies, something tells me that they're not the only CEO wh…

  4. comment
    Comment #49152191

    In the past "RTFM" or "LGMTFY" have been responses, so why not something like, well, "I'm not aware of the top of my head, you afaik . Also feel free to ask Claude on the technical…

  5. comment
    Comment #49134426

    If I may ask; what's your experience doing this with smaller models like gpt-5.x mini/luna on the lowest reasoning setting? Does it work well? I've been thinking of doing the same …

  6. comment
    Comment #49130309

    > It seems pretty unlikely they'd ever okay this intentionally as some sort of marketing. > Members of OpenAI's leadership team were actually in the middle of a Twitter spat with H…

  7. comment
    Comment #49119278

    I’m assuming, somehow, “Dario and Amanda” has become a glitch token.

  8. comment
    Comment #49119025

    Farming is a necessary activity and in most countries, they are also a politically influential group. The case for data centers in the age of AI is weaker, and the only effects for…

  9. comment
    Comment #49107137

    I had a Logitech ergonomic mouse and by default, the two extra buttons corresponded to forward/back, and I had gotten quite used to them for navigating codebases. It's a shame the …

  10. comment
    Comment #49106212

    I would hope that they really didn't move in the direction of having the model memorize image IDs, as that could be easily replaced with an embedding-based image search tool call. …

  11. comment
    Comment #49099729

    > LLM generated code is a ticking time bomb, and is going to poison projects. Given the recent Anthropic ruling and OAI settlements, and the general stance of courts to look the ot…

  12. comment
  13. comment
    Comment #49050839

    I could do this in the beginning of 2025. Unfortunately, given the over-proactiveness of model these days, I find that they end up inferring what my original request was and implem…

  14. comment
    Comment #49045113

    Well, it could make a note in its memory and reference it later. I don't know if such a statement from the LLM would actually cause a write to the memory in all cases, though.

  15. comment
    Comment #49032131

    > Perhaps being informed of your obligations when you create an account is insufficient I'm sure that if we were talking about a corporate entity, then people would have retorted w…

  16. comment
    Comment #49009479

    I think then we should ban these sorts of posts about the allegation of distillation, since being able to post the story but then warning accounts with comments about the hypocrisy…

  17. comment
    Comment #49009438

    Honestly, it wouldn't surprise me if they just found evidence of distillation once in 2025 against some Chinese AI lab, and they've been lying about the rest to create a narrative.…

  18. comment
    Comment #48983471

    Everyone’s saying that it looks like Codex but TBH it just looks like all the AI chat websites on the side and some frequent actions on the top.

  19. comment
    Comment #48966411

    It was always intended to be a documentation site, see https://stackoverflow.blog/2011/06/13/optimizing-for-pearls-... and similar.

  20. comment
    Comment #48957132

    We had autorun.inf in the past installing automatically from any random USB drive[1]. The fun days where you always feared contracting malware if you so happened to plug a random U…

  21. comment
    Comment #48902679

    I wonder if there's a design decision documented somewhere that makes the existing graph databases like Neo4j, etc. not good enough for Youtrack's use case.

  22. comment
    Comment #48902276

    Great article. What does the (organizational) process look like to convert one of these specs to a processor product, does it go through a committee like the C++ standards?

  23. comment
    Comment #48888762

    The article conflates general use of LLMs with LLMs for programming and is a worse article for this reason. As an example, I already heavily leverage LLMs to ask questions about un…

  24. comment
    Comment #48888707

    Such a utopian future is unlikely to materialize however. The salary that one gets paid is backed by the generated (and perceived) value of the work they did, and if people do not …

  25. comment
    Comment #48887609

    So much this, the other day I wanted to set up a project running in K8s similar to our other modules at work, and it he thing ended up writing unit tests for a hello world implemen…