News for hackers. Stuff that matters.

ahmadawais

ahmadawais on Hacker News

Re: on Friday August 14, 2026 @01:28AM (#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 cybersecurity, setting a new standard among open models

Tech Blog: https://z.ai/blog/glm-5.3

Re: on Thursday August 13, 2026 @07:46AM (#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 Agent workflows, max for complex tasks. Native OpenAI Responses API support, optimized for Codex with one-click setup.

V4 Pro is now available on app/web. Try it via “Expert Mode”. V4 Pro is also available via API. Model names remain unchanged—please refer to the API docs for setup details.

Re:Show HN: Command Code GOAT, $10/month for $70 of credits across 30 ... on Wednesday August 05, 2026 @04:56PM (#49188892)
i thought that's what we're supposed to do. it has the link too btw.

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

Posted by ahmadawais on Wednesday August 05, 2026 @04:35PM
from the show-hn dept.

https://twitter.com/CommandCodeAI/status/2085039006203711649

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 create the GOAT plan?At Command Code, we're incessantly curious about 1) open models, 2) how to get the best value out of them, and 3) how to make that value accessible to everyone. The GOAT plan is our answer to all...

( Read More... | 2 comments | 6 points | on HN )
Re:Qwen 3.8-Max and Qwen3.8-27B are going open weight on Sunday August 02, 2026 @10:48PM (#49150668)
can't wait for it. i think they'll do 35B variant as well.
Re:Qwen 3.8-Max and Qwen3.8-27B are going open weight on Sunday August 02, 2026 @10:35PM (#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!
Re:How did we make DeepSeek outperform Opus on Tuesday July 07, 2026 @08:37PM (#48825946)
see that's what i was saying.

in v1 we'll have a super strong extension api — week out probably.

Re:How did we make DeepSeek outperform Opus on Tuesday July 07, 2026 @06:25PM (#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 many versions of this on pi, oc, or whatnot. This is already live in our hardness command code for almost two months now and we are now fixing one million tool repairs per one trillion tokens.

also decided to open source Command Code by v1 release, so hopefully end of the month. https://www.youtube.com/watch?v=laEzOCgtK6c (live stream on this)

Re:How did we make DeepSeek outperform Opus on Tuesday July 07, 2026 @06:22PM (#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 their models after lots of prefix work.
Re:Building Effective "Agents" on Monday December 23, 2024 @01:16AM (#42492245)
Have you seen any CS bots those are agents. We built an email agent example among many other at https://Langbase.com/docs
Re:Building Effective "Agents" on Monday December 23, 2024 @01:07AM (#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.
Re:Building Effective "Agents" on Monday December 23, 2024 @12:54AM (#42492155)
Couldn’t agree more. Btw what’s your use case?
Re:Show HN: State of AI Agents 2024 – 184B tokens · 786M runs analyzed on Thursday December 12, 2024 @04:16PM (#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?
Re:Show HN: State of AI Agents 2024 – 184B tokens · 786M runs analyzed on Wednesday December 11, 2024 @02:56PM (#42392115)
I was surprised by the Mistral usage — i think Llama has taken over the open-source LLM scene lately.

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

Posted by ahmadawais on Wednesday December 11, 2024 @02:45PM
from the show-hn dept.

https://langbase.com/state-of-ai-agents

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, but this one’s different—it’s interactive! That's very much intentional.My team and I have been up for the last 21 hours putting together this report. This was a looot of work, so I hope y'all like it.Introducing …...

( Read More... | 4 comments | 5 points | on HN )