brimtown

This is the premise of Natural Language Autoencoders.

https://www.anthropic.com/research/natural-language-autoenco...

The best writing on this is the "agent principal-agent" problem, which correctly frames the problem of agents and code review in terms of trust.

This is why the solutions for high-trust environments (small teams) and low-trust environments (big companies, open source projects) will be different.

https://crawshaw.io/blog/agent-principal-agent

This is wonderful. Consider decoupling the core from Emacs, or packaging in a way that doesn’t require it as heavily.

I’ve been doing my own exploration of terminal ASCII games via Dwarf Fortress instead of SimCity. I’ve learned that letting a coding agent play is an interesting way to get feedback as well :)

https://github.com/brimtown/claude-fortress

“standardize the intersection, expose the union” is a great phrase I hadn’t heard articulated before

I’m currently letting Claude build and play its own Dwarf Fortress clone, as an installable plugin in Claude Code

https://github.com/brimtown/claude-fortress

There is a PermissionRequest hook [1], along with Notification

https://code.claude.com/docs/en/hooks-guide#hook-events-over...

It must be newer because Opus never seems to know about it, and the claude-code-guide tool that fires occasionally misses it

This is @simonw’s Lethal Trifecta [1] again - access to private data and untrusted input are arguably the purpose of enterprise agents, so any external communication is unsafe. Markdown images are just the ones people usually forget about

[1] https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/

I have a soft spot for these JS fuzzy matchers, but there are so many that it’s worth talking about about the specific tradeoffs you chose / ideally offering an interactive comparison like μFuzzy does:

https://github.com/leeoniya/uFuzzy

Had hoped to see Neural Cellular Automata [1] mentioned as an extension of continuous, learnable automata.

[1] https://distill.pub/2020/growing-ca/

I work in this building - it’s a wonderful experience walking through it every morning, and will be sad to see it go!

You might be interested in https://www.datadoghq.com/blog/engineering/computing-accurat...

Disclaimer: I work there/built the TypeScript implementation of the library

See also https://github.com/Munter/subfont#readme (or https://www.gatsbyjs.org/packages/gatsby-plugin-subfont/ for Gatsby sites).

> Q: If I have to include this token with every request, where should I store it?

> A: Typically, you would store it in the localStorage, after the user logs in and gets the token.

This seems to contradict Auth0's guidance to not store tokens in localStorage since it's vulnerable to XSS: https://auth0.com/docs/security/store-tokens#don-t-store-tok...

Dan Abramov's is very good: https://overreacted.io/

Thank you! We have plans to build many more frontends in the coming years, so it felt like an appropriate time to step back and see what other solutions were out there.

For the e-commerce part of it, it's a custom API written in Scala that handles our inventory, warehouse, and fulfillment needs. As well as interfacing with Stripe for actual order processing. Want to get that team to write their own blog post as several people have asked about it!

Sharing a blog post that my team wrote on some of the benefits we saw from using Gatsby / a static frontend architecture when building https://shopflamingo.com: https://medium.com/harrys-engineering/how-we-used-gatsby-js-...

In short, being able to scale to as many requests as your CDN can handle, with none of the operational overhead of a traditional web server, is really really nice.

The Dynamicland Twitter account has a bunch of fascinating demos of their work so far: https://twitter.com/Dynamicland1

It looks like tig: https://github.com/jonas/tig

Also fails google.com on mobile. http://motherfuckingwebsite.com/ however is a 99/100.

Cache: http://webcache.googleusercontent.com/search?q=cache:lV-hx4M...

Cached version: http://webcache.googleusercontent.com/search?q=cache:GJCV4xo...

Link should probably be changed to this: http://www.businessinsider.com/elon-musk-email-tesla-employe...

No worries! As someone only a couple years older than you, I have to say, congrats on making the move out there. It seems like you've got a lot of passion and commitment; wish I was in the Berkeley to take you up on the coffee.

It's marked as an email field, and if you enter a random string, it replies "Message sent!". Not trying to be pedantic or critical, I just figured he'd want to know if his goal was actually to gather emails.

Great idea. Just a heads up, the email validation in your index.js isn't functioning; it accepts any arbitrary string (or none at all).

Good call on ditching the extended pregnancy metaphor.

Previous post: https://news.ycombinator.com/item?id=7970809

I received one of these as a gift once. Played around with it for 2 minutes, then never used it again.

The main issue I had with it was that you had to 'hunt and peck' in order for it to register. Merely sliding your fingers around like on a standard keyboard would just register errant keystrokes.

Also, resting your palms had the same keyboard-mashing effect. It was cool to show off to others, but totally impractical for real use.

Has Coinbase posted a list of the "top 500" colleges that are supported, or are we left to guess? I signed up a few minutes ago and haven't seen anything yet.

Edit: Still not showing up. Kinda scummy to advertise this to college students and not follow through, especially in the heat of finals week.

>...the first of what will be numerous digital magazines published by FLM Seems like they'll be linking to subsequent magazines from that main page

Gives new meaning to the term 'growth hack'