Live data from Hacker News

Viewing profile — seamossfet

seamossfet

HN member
Joined
Sat, Jan 21, 2023, 6:55 PM UTC
HN karma
292
Public activity
45 items

About seamossfet

Working on CAD for drug discovery.

Talk to me about computational chemistry, bioinformatics, and molecular biology!

Recent public activity

  1. comment
    Comment #49012783

    I don't know if I agree with the premise that having access to AI results in dulling human intellect. I feel like to get to Terry's level you need a combination of passion and apti…

  2. comment
    Comment #49012695

    The big take away for is the fact that the ONLY reason why chatgpt was able to get to this counterexample was because of the knowledge of the person driving the conversation. I don…

  3. comment
    Comment #48799798

    Nothing wrong with vibecoding a toy project.

  4. comment
    Comment #48040193

    We're building a CAD for drug design, we often have to handle large and highly varied file formats. Protein structures, compounds, python scripts, lab notebook entries, instrumenta…

  5. comment
    Comment #48039489

    Does this provide gitflow to handle conflicts from multiple agents touching the same file system or is it purely for single-branch sequential iterations on the filesystem? I have a…

  6. comment
  7. comment
    Comment #47876199

    People often use "non-deterministic" to imply "unreliable" when that's not always the case. You can have an LLM that's clearly non-deterministic but also reliable for tasks.

  8. comment
    Comment #47768116

    Great article, but your site background had me trying to clean my laptop screen thinking I splashed coffee on it.

  9. comment
    Comment #47722401

    The hardest part about using agents to code for me has always been working in teams. When you can cut through huge parts of the code with a chainsaw, how do you review multi-thousa…

  10. comment
    Comment #47722116

    This is why I built [AI slop tool]. [Self promotion link to my vibe coded startup with no users]

  11. comment
    Comment #47722064

    A false dichotomy that segments typical replies into one of two groups. Group 1: A thinly veiled straw man that buckets everyone I disagree with, along with an attempt to appear as…

  12. comment
    Comment #47642027

    The problem with models like this is they're built on very little actual training data we can trace back to verifiable protein data. The protein data back, and other sources of tra…

  13. comment
    Comment #47641927

    This is awesome! The only limiter here is the resolution, I think this is fantastic for cellular level organelles but it doesn't quite get down to the same resolution something lik…

  14. comment
    Comment #47634356

    Honestly, this is a good thing. OpenClaw as a concept was rather silly to run such a heavy model for. If you want something like OpenClaw to work you really need to figure out how …

  15. comment
    Comment #47634235

    Honestly, it'd be really funny to try and make a CLAUDE.md file for slop maxxing.

  16. comment
    Comment #47618668

    I'm not convinced people who are doing real work on production applications with any sizable user base is writing code through only agents. There's no way to get acceptable code fr…

  17. comment
    Comment #47618611

    Oh my god, this comment gave me flashbacks to when I was writing android apps in Eclipse + ADT

  18. comment
    Comment #47618517

    > We very much still believe this That's good to hear, I might have jumped a little too quickly in my opinion. It's a bit of a Pavlovian response at this point seeing a product I v…

  19. comment
    Comment #47618440

    Yeah that's the disconnect though right? Even with the best frontier models, you need to do a lot of system design work, planning, and reviewing before you can let these models run…

  20. comment
    Comment #47618253

    Man, I wish they'd keep the old philosophy of letting the developer drive and the agent assist. I feel like this design direction is leaning more towards a chat interface as a firs…

  21. comment
    Comment #47614323

    I wonder how much of this is also used for audience segmentation for their advertisements? Linkedin ads are some of the most expensive out of any social media platform, but they al…

  22. comment
    Comment #47591965

    >But if your workload is not shifting from write-heavy to read-heavy, you inevitably will be responsible for a major outage or quality issue. I think that's actually a good way to …

  23. comment
    Comment #47591456

    >slop cannons I am stealing that phrase haha

  24. comment
    Comment #47591437

    Yeah, I'm not trying to defend slop. I don't think all means-to-end people are just in it for money, I'll use the anecdote of myself. My team is working on a CAD for drug discovery…

  25. comment
    Comment #47591342

    The public doesn't care about the code itself, they absolutely care about the quality and experience of using the software. But you can have an extremely well designed product that…