Hacker News: britannio

New comment by britannio in "Pocket TTS: A high quality TTS that gives your CPU a voice"

britannio — Fri, 16 Jan 2026 09:44:09 +0000

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...

New comment by britannio in "Can Coding Agents Do QA with a Browser?"

britannio — Mon, 01 Dec 2025 13:53:58 +0000

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

Can Coding Agents Do QA with a Browser?

britannio — Mon, 01 Dec 2025 13:53:58 +0000

Article URL: https://www.vibekanban.com/blog/does-playwright-mcp-unlock-autonomous-qa

Comments URL: https://news.ycombinator.com/item?id=46107408

Points: 4

# Comments: 1

New comment by britannio in "Solveit – A course and platform for solving problems with code"

britannio — Fri, 03 Oct 2025 00:31:14 +0000

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...

New comment by britannio in "MCP: An (Accidentally) Universal Plugin System"

britannio — Sun, 10 Aug 2025 20:48:08 +0000

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...

New comment by britannio in "Spaced Repetition Memory System"

britannio — Mon, 19 May 2025 08:10:53 +0000

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

New comment by britannio in "12-factor Agents: Patterns of reliable LLM applications"

britannio — Tue, 22 Apr 2025 17:51:29 +0000

looking forward to the new tool

New comment by britannio in "Rama, the 100x developer platform, is now free for production use"

britannio — Tue, 18 Mar 2025 22:42:36 +0000

> 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

New comment by britannio in "Fitness Trackers Are Only 67% Accurate, New Research Finds"

britannio — Sat, 15 Mar 2025 10:22:07 +0000

Why didn't they include Whoop or Oura?

Show HN: Slop Factory – UK's Shortest Hackathon Winner

britannio — Wed, 12 Feb 2025 12:28:59 +0000

I had three hours to build a website, so I used Cursor Composer to create a website that builds websites. Claude Sonnet generated the ideas for each of the 200+ websites and then created a one-shot implementation as a standalone HTML file embedded in an iframe.

Some of my favourites are in this thread: https://x.com/Britannioj/status/1889387050702610851

Comments URL: https://news.ycombinator.com/item?id=43024695

Points: 1

# Comments: 0

New comment by britannio in "Snyk security researcher deploys malicious NPM packages targeting cursor.com"

britannio — Tue, 14 Jan 2025 13:35:09 +0000

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

New comment by britannio in "Making AMD GPUs competitive for LLM inference (2023)"

britannio — Tue, 24 Dec 2024 11:55:57 +0000

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

New comment by britannio in "How we made our AI code review bot stop leaving nitpicky comments"

britannio — Sun, 22 Dec 2024 12:40:14 +0000

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

New comment by britannio in "Tldraw Computer"

britannio — Fri, 20 Dec 2024 17:31:41 +0000

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.

New comment by britannio in "Clay – UI Layout Library"

britannio — Thu, 19 Dec 2024 20:23:42 +0000

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

New comment by britannio in "We're forking Flutter"

britannio — Mon, 28 Oct 2024 21:26:42 +0000

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

New comment by britannio in "Collaborative text editing with Eg-Walker: Better, faster, smaller"

britannio — Fri, 27 Sep 2024 16:01:46 +0000

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.

New comment by britannio in "Rustpad is an efficient and minimal open-source collaborative text editor"

britannio — Wed, 18 Sep 2024 12:50:56 +0000

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

New comment by britannio in "Launch HN: Silurian (YC S24) – Simulate the Earth"

britannio — Mon, 16 Sep 2024 20:18:00 +0000

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

New comment by britannio in "Faster CRDTs (2021)"

britannio — Mon, 09 Sep 2024 00:19:10 +0000

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