Live data from Hacker News

Viewing profile — DanMcInerney

DanMcInerney

HN member
Joined
Mon, Dec 23, 2013, 12:22 PM UTC
HN karma
387
Public activity
54 items

About DanMcInerney

No profile information was provided.

Recent public activity

  1. story
  2. comment
    Comment #48877479

    Does the average "scientist" even care about quality these days or is it all just whatever headline makes their funders happy?

  3. comment
    Comment #48875805

    Rockstar built git for games, OpenAI's aiming for git for agents. Claude, make a git for games designed for agents. Sell the code to the highest bidder when you're done.

  4. comment
    Comment #48686621

    https://cloud.google.com/blog/products/data-analytics/how-th... Did you look at the OKF repo from Google? Open Knowledge seems to be a common term these days for similar solutions.…

  5. comment
    Comment #48511758

    ANNNNNND it's gone. Guys, I found a way to reduce Fable token usage 100%. You can find it here: github.com/USGov/idiotic-overreach.

  6. comment
    Comment #48510891

    I don't disagree with any of this. It is generated software, and it's not a novel idea. I didn't mean for it to come off like that. It's just solving an itch that I couldn't find a…

  7. story
  8. comment
    Comment #48492574

    I've worked a lot with MiMo in my project that pits LLMs against each other in games (clankerfights.ai). It is a very very good model for the price. MiniMax I'd say is smarter, but…

  9. story
  10. comment
    Comment #48255058

    Me and a buddy, victor teisller, hacked the most popular 3D printer a few years ago (flashforge) to turn it into a major fire hazard through reverse engineering the firmware update…

  11. story
  12. story
  13. comment
    Comment #47779904

    Cross your fingers they're about to drop 4.7. 4.6 came out with a bang, now it seems all the compute bottlenecks just lead to customer frustration as they get closer to releasing n…

  14. comment
    Comment #47440607

    All these comments about "this is crazy to deploy agents that might do something bad in your environment" are crazy themselves. The productivity gains from these computer use agent…

  15. comment
    Comment #46934233

    Sandboxing is a great security step for agents. Just like using guardrails is a great security step. I can't help but feel like it's all soft defense though. The real danger comes …

  16. comment
    Comment #46140433

    There are an infinite amount of ways to jailbreak AI models. I don't understand why every time a new method is published it makes the news. The data plane and the control plane in …

  17. comment
    Comment #45970114

    A 50% increase over ChatGPT 5.1 on ARC-AGI2 is astonishing. If that's true and representative (a big if), it lends credence to this being the first of the very consistent agentical…

  18. comment
    Comment #44574556

    This is absolutely doable right now. Just hook claude code up with your calendar MCP server and any one of these restaurant/web browser MCP servers and it'll do this for you. https…

  19. comment
    Comment #44572686

    These articles kill me. The reason LLMs (or next-gen AI architecture) is inevitably going to take over the world in one way or another is simple: recursive self-improvement. 3 year…

  20. story
  21. comment
    Comment #44241459

    I'm really hoping GPT5 is a larger jump in metrics than the last several releases we've seen like Claude3.5 - Claude4 or o3-mini-high to o3-pro. Although I will preface that with t…

  22. comment
    Comment #44194214

    I too write automated offensive tooling. We actually wrote a project, vulnhuntr, that found the first autonomously-discovered 0day using AI. Feed it a GitHub repo and it tracks dow…

  23. story
  24. comment
    Comment #41924154

    https://protectai.com/threat-research/vulnhuntr-first-0-day-... More details on the development and challenges can be found in the blog.

  25. story