News for hackers. Stuff that matters.

_boffin_

Re:Astra can read and write weights to improve Qwen on Monday November 02, 2026 @02:04PM (#50341905)
This is straight black magic. llama 70b, let’s see what we can push you to
These need to have an audit trail. Making it centralized is an addition, no?
Re:ChatGPT and Codex usage limits merging on Sunday November 01, 2026 @01:42PM (#50328399)
As a Pro user, am not a fan of this.
Just looked and we're burning around ~3%, but that's across everything / everyone.
Re:Giving chat feedback gives Anthropic your data on Tuesday October 27, 2026 @11:45AM (#50261046)
You can disable their datadog telemetry?
Re:OpenAI models are coming to Google Cloud on Wednesday October 21, 2026 @03:17PM (#50186087)
Microsoft has had ZDR for inference since pretty much the beginning. Just needed to fill out a form and get approved.
Re:Why aren't AI companies being charged for hacking? on Monday October 12, 2026 @11:29AM (#50057863)
A gun manufacturer directly hires a company to test their new line of 9mm handguns. The company that was hired, they go back to their office and pops off a few rounds. They go through the drywall and hit someone. The gun manufacturer could def face charges in this situation.

Edit: your analogy is wrong just due to Irregular being hired by them rather than just being a customer of them

i'm sorry, but oh shit, we can now play battleship against aliens!

Edit: i do love the pages and what you've done w/ the data. What was the hardest part about making it?

Re:Grok 4.7 on Monday September 21, 2026 @01:31PM (#49790429)
Does not work for Claude, at least for me and I put it as the system prompt
Re:Jev: New frontier model 40-400x cheaper and 20-200x faster on Tuesday September 15, 2026 @08:10PM (#49720553)
Any relation / inspiration to GLiClass?
i really thought "Apple Intelligence" is the addition of data into Knowledge.db, but i guess not.
Re:OUI-1: world's first model for Generative UI on Wednesday September 09, 2026 @11:39AM (#49628359)
> The problem with that is that it only works with simple, least interactive UIs.

I believe that's incorrect. you can define the architecture to be able to provide data based on information from the frontend and the components just need to define a query and data structure or something -- will have a prototype soon

Re:OUI-1: world's first model for Generative UI on Wednesday September 09, 2026 @12:50AM (#49621151)
Oh... amazing. just had a vision of being able to be in a meeting and talk through an User Interface design / review, while in a zoom meeting or whatever.

...i like.

---

- Design system / Component lib

- Live view of what components, tokens, other things... on the left side of the screen.

- You're in the meeting and talking while talking and transcribing and doing the full duplex voice. You say, "Find what tables and customizations we have available" and the list starts to filter to tables and customizations.

- "Let's add that table to the page; left side; 3/4 width of page. Headers should be static for vertical scroll, ..."

- The table is added to the page.

- "Nah, i don't like it. Let's change that table component to have larger headers..."

yes, i like--let's see what Astra Pro pops out with.

One thing I’ve done is a few books and check what branch / work tree user is on. Allows for more fidelity than even this. Works quite well.

I just wish they allow for getting inside subscription pricing vs outside subscription pricing easier

Re:Training AI to Paint with Code on Monday August 24, 2026 @12:25AM (#49415169)
I think this actually might be one of the best ways to train people to use AI. I can see this honing people's prompting abilities and expressiveness, along with constraints and desired outcome.

Wild the possibilities

Re:How Complex Systems Fail on Sunday August 23, 2026 @08:29PM (#49413977)
Did love Team of Teams. Need to check out the other
Re:My agent.md to improve LLM-assisted code quality on Sunday August 23, 2026 @06:19PM (#49413190)
One thing I don’t get with a lot of these agents.md and other skills are… why not throw as much mechanical checks and other stuff at the repo to constrain as you want instead of asking a non-deterministic agent (squishy or non-squishy) to maintain it.

With the mechanical routes, we get checks, failures, and so much more. A bit wild to me.

Make an agent operate within defined constraints and yell at it when it doesn’t.

Re:How Complex Systems Fail on Sunday August 23, 2026 @02:50PM (#49411350)
Check out the book called, The Logic of Failure. I think you’ll like it
Nice. seems like this converges on something i built called https://Tangents.chat, specifically the "Context complier", which can be seen here (https://tangents.chat/demo) (click Context in the top right after entering the demo).

Looking forward to looking more at ThoughtDAG.

Visual: https://i.ibb.co/NRHSFrg/tangents-context-complier.png

Thanks! I don’t know if ALL markdown is going to be implemented or not yet, but not out of consideration.

Question: anything that caught your eye in regards to this project?

Found out about 45 min ago about pretty much the lack of mobile creature comforts.

Working on mobile clients right now. Will push improvements tonight.

Doesn’t need to be built by node. It’s standalone.
Dependency-free means zero runtime dependencies, not no dev tools. Could have explained that better.

Show HN: Writemark, a dependency free web component for inline Markdown editing

I like writing Markdown, but do not like writing it inside a plain textarea.I wanted something I could use anywhere by dropping in a single web component:```<writemark-editor name="body"></writemark-editor>```That became Writemark.It renders Markdown while you write, but Markdown remains the value you read, store, and submit. It also has source, split, and preview modes, along with...

( Read More... | 27 comments | 24 points | on HN )
Re:NotebookLM is now Gemini Notebook on Thursday July 16, 2026 @07:27PM (#48941615)
Did this while on a run for the past few days. The thing / interaction model I’ve been waiting for is here finally.
I'm liking the idea of the project, but you're spending too many tokens on critic prompts for things that should be deterministic.
Re:Linear is always a lagging indicator on Tuesday July 14, 2026 @08:03PM (#48914565)
> any issue tracking tool that is used instead as a visibility tool by higher-ups to get a view into what their organization is doing is also lagging

I completely agree! There's so much additional information strewn throughout the organization that allows for a much more vibrant picture of what's going on

Graph based code generation where code doesn’t reside in files in the typical sense. On insertion, modification, and deletion, constraints are checked / ran to see if the change is valid and can be done or not.

Older »