Live data from Hacker News

Viewing profile — lodovic

lodovic

HN member
Joined
Fri, Feb 28, 2020, 11:43 AM UTC
HN karma
737
Public activity
450 items

About lodovic

Software engineer for an energy giant

Recent public activity

  1. comment
    Comment #49228504

    Try refreshing Firefox. On opening it shows two recommendations for Google; a large "VPN" button in the address bar; a toast asking me for my weather location; the address bar trie…

  2. comment
    Comment #49205910

    I think babysitting the AI would be a better term than vibe coding. At work they call it "AI assisted engineering" and "synthetic coworkers"

  3. comment
    Comment #49002556

    I have a separate lan for untrusted devices, I only use whitelisting. No public DNS for these devices.

  4. comment
    Comment #49002504

    I'm always wondering how hard it would be to just remove the hardware for spying. Just keep enough hardware to make it a dumb panel, remove the webos logic boards, wifi antenna, et…

  5. comment
    Comment #48830861

    This can be very useful for urban planning. you could have an agent investigate the optimal spot for a new datacenter, examine solar power installations, and so on.

  6. comment
    Comment #48828838

    I have the same sentiment. Who assures me this video isn't sent to the manufacturer for "quality control" reasons? Can it be used in court in case of an accident? Will my insurance…

  7. comment
    Comment #48793289

    That would put full blame on the tech staff and let the C-suite get away. The success of a software product is measured by sales and user base, so the more successful their sales a…

  8. comment
    Comment #48421770

    I don't think they'll let the chain of managers above you handle the llm directly. That is just too much risk of incompetence. Instead, there will be micro teams (1 dev, 1 sre, 1 p…

  9. comment
    Comment #48421695

    The first time I pasted a screenshot of a PR review thread, adding just "I had some review comments, fix them" - and it perfectly solved everything, made small commits, and pushed …

  10. comment
    Comment #48386751

    I now foresee a future where law firms have models trained on all the transcriptions of individual judges, lawyers and prosecutors, and run agents against them to decide on the opt…

  11. comment
    Comment #47908162

    I doubt everyone will still be carrying phones as we know them in a decade, so we might indeed be headed for a future where governments keep giant databases of biometric informatio…

  12. comment
    Comment #47861602

    That domain is for sale. This whole thread sounds like one of these "I sell ai agents as a saas and make 30k/month" stories.

  13. comment
    Comment #47819903

    "I have an error when i click on the orange button, see screenshot. fix it."

  14. comment
    Comment #47813431

    Exactly, these hotel chains guarantee a sort of minimum quality level which is sufficient for most people. No surprises.

  15. story
  16. comment
    Comment #47192395

    Grok is quite good for explaining tweets, summarizing meme videos and chatting about celebrities. But chat and image inference only, it was performing really poor in agentic work t…

  17. comment
    Comment #47190913

    Addidionally: Why wasnt X.ai considered before Openai? also noted a lot of hate from Musk towards Anthropic lately.

  18. comment
    Comment #46932018

    I made something similar to this project, and tested it against a few 3B and 8B models (Qwen and Ministral, both the instruction and the reasoning variants). I was pleasantly surpr…

  19. comment
    Comment #46538398

    I tried to sign up for Gemini this weekend but gave up after an hour. I got stuck comparing their offerings, looking for product pages, proper signup, etc. Their product offering a…

  20. comment
    Comment #46418374

    I love these thought experiments. Looking at the code size, it would have been possible for someone to come up with this back in the days, similar to the idea of a million monkeys …

  21. comment
    Comment #46372970

    I always start in the Claude CLI. Once I hit the token limit, I can do two things: either use Copilot Claude to finish the job, or pick up something completely different, and let t…

  22. comment
    Comment #46351916

    I actually get more mileage out of Claude using a Github Copilot subscription. The regular Claude Pro will give me an hour or up to 90 minutes max, before it reaches the cap. The G…

  23. comment
    Comment #46324175

    So you buy a new TV, unpack and install it, and then when the whole family is gathered around, you suddenly get this confirmation on the TV if you agree with their T&C. Are you sup…

  24. comment
    Comment #46324146

    Not everyone feels like that. Yesterday the app of my tv provider on my Samsung TV home screen suddenly shows a Prime icon in its place, prompting to install the app if you use mus…

  25. comment
    Comment #46323938

    Thank you