Live data from Hacker News

Viewing profile — scottyeager

scottyeager

HN member
Joined
Sun, Dec 03, 2023, 5:10 AM UTC
HN karma
114
Public activity
60 items

About scottyeager

No profile information was provided.

Recent public activity

  1. comment
    Comment #48727555

    The next generation of models are currently being withheld from general release. Beyond that, there's still a lot of room to compete on price and also independence from the US labs…

  2. comment
  3. comment
    Comment #48566219

    Did you mean Sonnet and Opus?

  4. comment
    Comment #48491488

    Back then they were both written in Go too. OpenCode was rewritten in TypeScript after Crush got the rename.

  5. comment
    Comment #48446676

    Community and listener supported radio stations can be a great resource. I discover a lot of music via a local station I discovered by surfing on the FM dial. Most stations offer o…

  6. comment
    Comment #48247305

    Refusing future applications to adjust status would be one thing (still wrong, in my opinion). The fact that they are canceling pending applications is simply evil. There will be s…

  7. comment
    Comment #48223291

    It's just too bad Emacs doesn't also include a decent text editor, right?

  8. comment
    Comment #47684649

    New Nvidia Parakeet release does both offline and streaming. English only and outperforms v2 error rate in offline mode while being very competitive with v2 in high latency streami…

  9. story
  10. comment
    Comment #46761346

    Aider isn't abandoned, but it feels like it's basically in maintenance mode at this point. Updates over the last year were limited to small improvements and fixes. There are some f…

  11. comment
    Comment #46527656

    Do you mean to say Zed wasn't vibe coded? There's actually another comment on this post describing how someone is using Opus 4.5 to work on Zed. Given how forward the AI features a…

  12. comment
    Comment #46434576

    Happens to me even with an ad blocker.

  13. comment
    Comment #46363593

    "Significantly Enhanced Multi-Language Programming, Built for Real-World Complex Tasks"

  14. story
  15. comment
    Comment #46352195

    Not the OP, but I did release my source :D https://github.com/scottyeager/Pal My tool can read stdin, send it to an LLM, and do a couple nice things with the reply. Not exactly RAG…

  16. comment
    Comment #46352087

    I'm not the OP, but I did build a tool that I use in the same way: https://github.com/scottyeager/Pal Actually for many cases the LLM already knows enough. For more obscure cases, …

  17. comment
    Comment #46341270

    Older cars don't have these systems. Also they are easy to bypass with a dummy buckle. There are counties where seatbelt usage is far less common than the US.

  18. comment
    Comment #46309024

    As others have mentioned, a firewall might have been useful in restricting outbound connections to limit the usefulness of the machine to the hacker after the breach. An inbound fi…

  19. comment
    Comment #46232987

    On Linux, the default init program is usually systemd. The main job of the default init program is typically to be a process manager. That is, it starts other programs and can rest…

  20. comment
    Comment #46118033

    You can read that 3.2 is live on web and app here: https://api-docs.deepseek.com/news/news251201 The pdf describes how they did "continued pre-training" and then post training to m…

  21. comment
    Comment #45471644

    Personally I found the mini SWE-agent to be a very approachable introduction to building agents: https://github.com/SWE-agent/mini-swe-agent There are a number of free and cheap LL…

  22. comment
    Comment #45241005

    I just did some code to display digits on my APC Mini's 8x8 light grid: https://github.com/scottyeager/pressed/blob/main/controllers... By using the three available colors on my ol…

  23. comment
    Comment #45077061

    Fast inference can change the entire dynamic or working with these tools. At the typical speeds, I usually try to do something else while the model works. When the model works real…

  24. comment
    Comment #45076951

    They have a "max" plan with 120m tokens/day limit for $200/month: https://www.cerebras.ai/blog/introducing-cerebras-code

  25. comment
    Comment #45076815

    Haven't seen any issues like this while using a key from their subscription plan: https://www.cerebras.ai/blog/introducing-cerebras-code