Live data from Hacker News

Viewing profile — ahmadawais

ahmadawais

HN member
Joined
Thu, Sep 03, 2020, 7:16 PM UTC
HN karma
23
Public activity
23 items

About ahmadawais

Founder & CEO at ⌘ Command Code. Award-winning open source engineer, angel investor, and NASA Ingenuity code contributor. Google Advisory Board member. Ex-VP Eng at DX Rapid (acquired by Nokia). Microsoft MVP and 6x GitHub Star (ranked #1 trending JavaScript dev). Also founded Langbase.

Recent public activity

  1. story
  2. comment
    Comment #49295030

    Introducing GLM-5.3: Built to Code. Ready for Cyber Defense. - Top-tier coding and agentic capabilities, achieved through post-training on the 743B base model - A major leap in cyb…

  3. story
  4. comment
    Comment #49284565

    We’re launching DeepSeek-V4-Pro today! Major Agent upgrades with strong production gains! Flexible reasoning effort for V4-Pro & V4-Flash: low for simple tasks, high for daily Agen…

  5. story
  6. comment
  7. story
  8. comment
    Comment #49188892

    i thought that's what we're supposed to do. it has the link too btw.

  9. story
    Show HN: Command Code GOAT, $10/month for $70 of credits across 30 models

    Founder here, we launched the GOAT plan for Command Code today: $10/month for $70 in credits, usable across 30+ open and closed models. With deals it goes further, past $100. Why c…

  10. comment
    Comment #49150668

    can't wait for it. i think they'll do 35B variant as well.

  11. comment
    Comment #49150595

    > Next week, the open weights of Qwen3.8-Max will be released, and Qwen3.8-27B is also going open-weights to meet you all!

  12. story
  13. comment
    Comment #48825946

    see that's what i was saying. in v1 we'll have a super strong extension api — week out probably.

  14. comment
    Comment #48824839

    Thanks! I've seen many developers use the entire tweet as a prompt to improve their harness. If you trace errors, you can find tool call failures per billion tokens. I've seen like…

  15. comment
    Comment #48824808

    probably yep, i doubt they'll be able to maintain that well. we did a lot of work improving MiMo's cache thrashing, it was pretty bad early on. Now we're seeing 97% cache rate on t…

  16. comment
    Comment #48820183

    hey HN, sharing harness engineering deep dive on tool calling repairs for open models. i've been thinking about why "open model bad at tool calling" is almost always a harness prob…

  17. story
  18. comment
    Comment #42492245

    Have you seen any CS bots those are agents. We built an email agent example among many other at https://Langbase.com/docs

  19. comment
    Comment #42492209

    This was fun to read. Thanks for sharing. Our memory agents are built somewhat like this but way too much going on in there to make them prod ready.

  20. comment
    Comment #42492155

    Couldn’t agree more. Btw what’s your use case?

  21. comment
    Comment #42403426

    Spending 100+ hours on this, getting to know people who read this was the point after all. Pretty standard practice everywhere? What did I miss?

  22. comment
    Comment #42392115

    I was surprised by the Mistral usage — i think Llama has taken over the open-source LLM scene lately.

  23. story
    Show HN: State of AI Agents 2024 – 184B tokens · 786M runs analyzed

    hello everyone, my first post! AA here, founder of ⌘ Langbase.com — we are a developer platform for building and scaling serverless AI memory agents. I know surveys can be boring, …