Live data from Hacker News

Viewing profile — aenis

aenis

HN member
Joined
Thu, Jun 24, 2021, 10:43 AM UTC
HN karma
1,281
Public activity
414 items

About aenis

No profile information was provided.

Recent public activity

  1. comment
    Comment #49235787

    Polish living standard in major metro areas are significantly above Belgian standards. I lived in Poland and Belgium, among a few other places, and I'd choose Poland over Belgium f…

  2. comment
    Comment #49224256

    Yup. Where I work we invited a bunch of people circa May 2023: a few top tier academics, a few government and NGO officials in charge of our industry, and a few startup founders. W…

  3. comment
    Comment #49206243

    Its a cool demo, but its gpt-3.5 level stupid, or worse. edit: Ok, I will self-apologize. Its apparently a 3B model. Mighty impressive for what it does.

  4. comment
    Comment #49202498

    I suspect it must depend on how one manages their codebase - wrt to docs, ADRs, and general guardrails. For me it is not great for design work - Fable is way better, and 4.8 was co…

  5. comment
    Comment #49201784

    I managed to lose around $300 in credits I had saved for some emergency /fast sessions the following way: switch to Fable. Work on the design. Downgrade to Opus for the build. If a…

  6. comment
    Comment #49201741

    I do the same, and generally have good results, but it does stupid things with gusto. I'd open a blog with "weird things Opus did". Today it launched a swarm of cpu-hogging process…

  7. comment
    Comment #49195154

    Use google pre-ga stuff at your own risk. Fine for POCs and cool demos, absolute misery in scaled prod.

  8. comment
    Comment #49180136

    Yeah, I think thats a valid edge case - and a manageable one. If you are expecting a call from a doctor, lift the firewall for a while.

  9. comment
    Comment #49179216

    I never responded to an unknown or caller id hidden in 20 years. I am just fine, dont think I lost anything of value. I also asked my parents and inlaws to adopt the same approach.…

  10. comment
    Comment #49179180

    I dont think so. The LLMs are trained to play it safe and avoid responsibility for hard decisions. No commercial model will say "No, I wont connect your call, I dont think you are …

  11. comment
    Comment #49179166

    The advice I gave to my folks -- hard ignore any contact attempts not initiated by them. Dont read, dont answer the phone except from recognized numbers. I think thats the only way…

  12. comment
    Comment #49165725

    If you are a decision maker, you might find your personal stuff subject to a subpoena for any number of reasons. Antitrust, insider trading, harassment suits, all sorts of legal fi…

  13. comment
    Comment #49165090

    This is what gets people subpoena'd and their entirely private messages scrutinised. Happened to a lot of people, including a friend of mine who's affair became a matter of public …

  14. comment
    Comment #49162028

    My guess is their strategy is to aim for clueless developers, with more focus on "proactivity" with Fable and very large models. I have a few non-technical friends who dabble in AI…

  15. comment
    Comment #49161949

    Same experience here. I settled on Fable for design, Opus for build routine, and every now and then I'd try out the Chinese models. In my experience they do fine on small codebases…

  16. comment
    Comment #49126564

    Ekhem. When Chrome was announced there wasnt Rust. And Java was a programming language for slow moving systems, with many a flaws and its own classes of footguns. I dont think they…

  17. comment
    Comment #49045555

    Same here. For now there is value. Only today Opus 5 suggested a really bad but totally workable approach to an edge problem. It would work by putting a lot of undue stress on infr…

  18. comment
    Comment #49044494

    It does, when you explicitly ask you to do it. Hence the need for experienced devs running those models.

  19. comment
    Comment #49044437

    We have been heavily using agentic coding in my place, and what is emerging is people who used to be tech leads or architects are now back to producing code, and what would require…

  20. comment
    Comment #49044398

    "I wonder if there's a correlation between me refusing to use LLMs and me being happy to read a novella-sized PDF about them." Well, one possible explanation is that you have time …

  21. comment
    Comment #48984728

    Their pace makes me wonder how effectively do frontier labs protect their weights against motivated, capable adversaries. By now the value of something like Mythos is well in doubl…

  22. comment
    Comment #48957069

    The models are already brilliant at that. My own todo app generates 128x128 pixel art icons for my todo items. They are mind blowingly creative and funny.

  23. comment
    Comment #48956751

    Even boring, slow moving companies are well on their way to eradicate the last traces of oracle java. We kicked the last of that 2 years ago, despite having >3000 different systems…

  24. comment
    Comment #48890983

    I rebuilt a couple of games I used to play as a kid (jet set willy, mario, thrust, now i am working on Mercenary) - and for each I am also asking LLM to build an autopilot "AI" (wh…

  25. comment
    Comment #48883726

    For sure. What it gave me was I think similar to the Amstrad version of Thrust and since I originally played it on a Commodore PLUS/4 I had to tweak it a bit. The fist version also…