britannio

Debug mode?

Notably they have been using it internally since May. This is their v2.

timestamp is 47:45

SpaceXAI (Formerly xAI)

Many developers just want a good TUI and that's what it serves as.

Is this public? I'm interested in trying it.

12 prompts and my weekly usage on the 5x Max plan is up :(

This is impressive but in a sample I tried, it switched language on the second paragraph. I'm on a M4 Pro Macbook.

https://gist.github.com/britannio/481aca8cb81a70e8fd5b7dfa2f...

Hey HN, I wanted to share a few tips I use to get more out of coding agents connected to a browser!

I had access to GitHub Copilot as a student in early 2022 while learning Haskell and immediately realised that it would hinder my learning if I didn't turn it off and implicitly follow this understand, plan, execute, reflect loop.

AI products like Cursor have the notion of an 'autonomy slider' [1] that can fortunately be turned all the way down (disable Cursor Tab) but relying on this discipline seems fickle when with the right agentic loops [2] and context engineering, thousands of lines of code can be churned out with minimal supervision.

I've considered always working on two projects over a long timespan, one with no AI assistance, possibly in a separate IDE like Zed, and one in Vibe Kanban (my current daily driver) but this feels like an inefficient proxy to accelerating this four step learning loop with a tool like solveit.

Since the solveit product isn't released and seemingly isn't competing with solutions, is there an opportunity to convey how AI product developers should be thinking about amplifying their users and keeping them in the learning loop?

So far, I've seen Claude Code's Learning output style [3], and also ChatGPT's study mode but in these cases, the only product change is a prompt and solveit is more than that.

[1] https://www.latent.space/i/166191505/part-a-autonomy-sliders [2] https://simonwillison.net/2025/Sep/30/designing-agentic-loop... [3] https://docs.claude.com/en/docs/claude-code/output-styles#bu...

I discovered the "Layered Tool Pattern" a few days ago which exposes three tools to discover and execute an arbitrary number of service endpoints. https://engineering.block.xyz/blog/build-mcp-tools-like-ogre...

I used this throughout my computer science degree, and it worked a charm. Now I rely on it as a solid personal knowledgebase.

looking forward to the new tool

> We develop your entire backend according to your spec for 75% less cost than anyone else charges for a comparably high-quality implementation

Icing on the cake

Why didn't they include Whoop or Oura?

The lack of a bug bounty program doesn't prohibit them from rewarding reported vulnerabilities.

Some of the work from Tinycorp is: https://github.com/tinygrad/7900xtx

Only while a vendor is ahead of the others. We developers will favour a vendor with faster inference and lower pricing.

It was a cool thing... I expected a hacky demo that'd fall apart mid-way but it held up. The Macintosh SE in the office was cool too.

So cool. I wonder if it'd work for a Raspberry Pi Pico + https://pimoroni.com/picodisplay or similar devices.

The data is supposedly there: https://news.ycombinator.com/item?id=41975320

Joseph explains the algorithm on YouTube too: https://www.youtube.com/watch?v=rjbEG7COj7o

It's great work, combining the best of OT and CRDTs.

You can combine the best of both too: https://www.youtube.com/watch?v=rjbEG7COj7o

Andrej Karpathy states that LLMs are highly general purpose technology for statistical modelling of token streams [1]. For example, comma.ai uses transformers in their self-driving model which is far from a linguistic task.

[1] https://x.com/karpathy/status/1835024197506187617 [2] https://www.youtube.com/watch?v=-KMdo9AWJaQ&t=1010s

But in the eg-walker paper, you benchmark against Yjs rather than Yrs because Yrs performed worse?

It's actually the complete opposite: https://x.com/AviSchiffmann/status/1818460679680278709

Text selection doesn't work, and I can't navigate to the user's news.ycombinator.com profile; otherwise, it's neat.

I just finished the second half, it's a great book! I recommend doing one or two of the proposed challenges in each chapter to reinforce your understanding of the content.