Live data from Hacker News

Viewing profile — StanAngeloff

StanAngeloff

HN member
Joined
Thu, May 01, 2014, 7:11 AM UTC
HN karma
1,098
Public activity
162 items

About StanAngeloff

CTO by day, tinkerer by heart. Based in Sofia, Bulgaria. Currently building Flemma - a low-level AI workspace for Neovim (https://github.com/Flemma-Dev/flemma.nvim). Long OSS history: top 10 CoffeeScript contributor, compass-magick, php.vim, vagrant-shell-scripts. NixOS convert, shell & terminal believer.

GitHub: https://github.com/StanAngeloff | Mastodon: https://mastodon.social/@stanangeloff | LinkedIn: https://www.linkedin.com/in/stanangeloff/ | X: https://x.com/StanAngeloff | Blog: https://blog.angeloff.name

Recent public activity

  1. comment
    Comment #48502199

    > https://artificialanalysis.ai/agents/coding-agents?coding-ag... This is the full URL that does a composite average across DeepSWE, Terminal-Bench and SWE-Atlas-QnA. Models are me…

  2. story
  3. comment
    Comment #48421983

    One of the many SaaS products we use at Day Job chose to gatekeep its MCP behind an enterprise plan. A brief Claude Code session later and a better, more feature-full MCP than the …

  4. story
  5. comment
    Comment #48322028

    > [..] Early access users and teams inside Anthropic have been using dynamic workflows for a wide range of use cases [..] > ### Rewriting Bun with dynamic workflows > An example of…

  6. comment
    Comment #47938663

    All it took for Codex to resume a stalled Claude Code session: > I'm working with Claude Code on session aaaaaaaa-bbbb-1223-3445-abcdefabcdef which I'd like to hand-off to you, do …

  7. comment
    Comment #47853279

    I've actually had the same itch and decided to give it a go ... So far I'm one year into the project, learned a ton and highly recommend to anyone who'd listen - try writing you ow…

  8. comment
  9. comment
    Comment #47753779

    Dupe https://news.ycombinator.com/item?id=47753643

  10. comment
    Comment #47753744

    This is affecting lots of users (myself included) and has prompted an official status page update, so it's very much real for users, but I guess only on claude.ai. Are you using Cl…

  11. comment
    Comment #47753711

    Dupe https://news.ycombinator.com/item?id=47753643

  12. comment
    Comment #47753674

    Yes https://news.ycombinator.com/item?id=47753643

  13. comment
    Comment #47753663

    Officially down https://status.claude.com/incidents/6jd2m42f8mld Discussion: https://news.ycombinator.com/item?id=47753643

  14. story
    Tell HN: Claude Opus elevated "Internal server error" again

    No official report as of yet on https://status.claude.com/ however my team's sessions across different accounts have been ridden with errors the last 5-10 minutes. This is more of …

  15. comment
    Comment #47663637

    I did my usual thing today where I asked a Sonnet 4.6 agent to code review a proposed design plan that was drafted by Opus 4.6 - I do this lately before I delved into the implement…

  16. comment
    Comment #47663465

    I missed that from the long issue, thanks for pointing it out! My experience with Opus today was riddled with these to the point where it was driving me completely mental. I've rar…

  17. comment
    Comment #47663350

    I used to one-shot design plans early in the year, but lately it is taking several iterations just to get the design plan right. Claude would frequently forget to update back refer…

  18. comment
    Comment #47661440

    You say you've used it for months, I wonder if the example you gave was recent and if you've been noticing an overall degradation in quality or it's been constantly bad for you?

  19. comment
    Comment #47661215

    That is the kind of thing that I've been fighting by being super explicit in CLAUDE.md. For whatever reason, instead of being much more thorough and making sure that files are bein…

  20. comment
    Comment #47660970

    (Being true to the HN guidelines, I’ve used the title exactly as seen on the GitHub issue) I was wondering if anyone else is also experiencing this? I have personally found that I …

  21. story
  22. story
    Show HN: I built a full LLM chat client as a Neovim filetype

    I started Flemma because I wanted to bring my AI workload into Neovim. My workflow started with me living in developer portals - Claude Workbench, OpenAI Platform, Vertex (the horr…

  23. comment
    Comment #47417357

    https://status.claude.com/incidents/mhnzmndv58bt Sonnet is not affected, so far. EDIT: and inevitably 10 minutes into the Opus outage the dreaded 529 Overloaded on Sonnet appears.

  24. comment
    Comment #47306769

    I've been working on an AI workspace inside Neovim (and using the editor as the TUI). When I started, I asked myself, "Wait, WHAT?! Another one? Who would use this?" However the go…

  25. comment
    Comment #47154490

    Also affects Claude Code, not just API use (this incident was originally reported as "500s for public-api").