maxbaines

Cool, thanks for working on accessibility.

Great minds...

Agree this is a fact - we mark our glasses because of it. https://www.gov.uk/weights-measures-and-packaging-the-law/pr...

This is hardly surprising given - New partnerships with tech companies support Wikipedia’s sustainability. Which relies on Human content.

https://wikimediafoundation.org/news/2026/01/15/wikipedia-ce...

Thankyou

This should make you think..

I think as the article mentions garbage in garbage Out, we are more trusting and expect more. Coding assistants don't just need a good model, they need a good harness, these methods have also changed recently.

Not seeing this in my day to day, in fact the opposite.

I nearly always use Tailwind, had no idea there was even a Plus offering. Checking the site I see it now but it’s a subtle link. Also wonder if shad/cn had something to do with the reduced usage of plus.

Looks like a pretty useful offering, 128Gb Memory Unified, with the ability to be chained. IN the Uk release price looks to be £2999.99 Nice to see AI Inference becoming available to us all, rather than using a GPU ..3090etc.

https://www.scan.co.uk/products/asus-ascent-gx10-desktop-ai-...

I am very much pro AI and use it daily for everything from code to product photos, and games. But I feel these moments are one of the few you actually want to keep AI away from. Imagine looking back in hopefully 50years at an AI image.

There are plenty of slag heaps (spoil tips) near coal plants, wonder how it could work with those? I guess the specific heat capacity is greater..

This type of plant is generally used for emergency power to balance the grid, whilst other plant come online.

Really like the idea of this, and good timing for me. Will give this a try over the weekend.

Have a soft spot for digg

Best thing I have seen on HN in ages. Also interesting for a CNC geek.

Pelican riding a bicycle is only official when it comes from Simon Willison https://simonwillison.net/2025/Jun/6/six-months-in-llms/

good bugs lol

Yeah lets just kill all the bugs, good move.

Reminds me of http://www.gamtech.com/oakflat.aspx loved blowing triggering SCRAM as a kid

Thankyou for the reminder, long term Node-RED user here, I recently looked again at n8n and wondered why I never took it to far, this is the reason. When you see a git icon and repo it's easy missed.

System Prompt aside and not that critical today, however you look at it you are stuffing context. MCP is good at that and it works in most AI‘s.

Say what you will about it. MCP surely has to be your primary interface?

When a competitor buys you this happens. There are plenty of exceptions, however.

Love them, and your style. I will likely buy these.

I agree with your opinion here, not sure we should refer to it as MCP security however, given that 'MCP doesn't have security flaws in the protocol itself'

Books?

Less and less now actually. Synthetic data is now being used on most new models as the public data runs out.

This is the first thing I do when using LLM's to create code. So we can and I do have LLMs writing documentation.

In my domain IIoT, I even created a yaml structure to make this easy. https://unsframework.com (wip)

Dyson 2.0