AndyNemmity's comments

On: A font that reads what you wrote

[AndyNemmity]

yup, just broken for me.

On: Doing Everyone Else's Job

[AndyNemmity]

I've been at the top of the org chart. I hated it. I intentionally decided to go back to engineering.

"Appreciation" in this case means, promotions. I don't want them, and would actively change jobs if you forced it on me.

So I am more than happy to just do a great job at my job. I do not desire or want anyone to notice me in any particular way. I want to be paid a reasonable amount, and make sure everyone that uses anything I touch is happy with the experience.

That's a great life. I don't understand why anyone would think that caring about things matters at all.

There's a massive difference between your users, and peers appreciating you, and management appreciating you.

Management doesn't know anything. Why would I value their appreciation?

I care much more about my intelligent peers, or even commenters here, than what a non technical person thinks.

On: Negativland, Culture Jamming, and the Art of Making Something New

[AndyNemmity]

I played Negativland on my radio show which was played on pirate radio in LA through Killradio.org

I remixed them, music, and dense political talks for a one hour show.

On: Flock cameras used to arrest a child for playing on a swing?

[AndyNemmity]

The details are they were caught with surveillance cameras, we don't know which provider.

On: Astra and Fable still hack on simple variants of alignment evals from 2025

[AndyNemmity]

Exactly, I wrote a blog post in what feels like a long time ago on this topic.

https://vexjoy.com/posts/positive-framing-agents-skills/

[PotatoPrime → AndyNemmity]

Interesting read, thanks for re-sharing!

I noticed your joy-check link 404's now... I tried poking around your /skills/ folder but didn't find it easily. Should you still have that available I'd love to check it out.

edit: Found it if others are looking: https://github.com/notque/vexjoy-agent/blob/main/skills/code...

[AndyNemmity → PotatoPrime]

Oh, thanks for letting me know. I need to fix that.

On: David Sacks: OpenAI and Anthropic Don't Need Regulations to Pace Frontier Models

[AndyNemmity]

I mean, they said it was clearly an anti trust issue. It is.

It is also true that nothing in law is currently clear, or consistent.

Both are true. But you stated it's one or the other.

On: How AI text watermarking works

[AndyNemmity]

I have done it for a long time now. It's actually pretty straight forward to do it, but you have to run it in a pipeline, and you have to add deterministic checks as well.

There was an odd key to unlocking it sounding like a human. I spent like a month on this topic last year, and I randomly stumbled upon something that ended up massively improving generated tests.

It was a shot in the dark after failing so often. And then it suddenly sounded good.

[nonethewiser → AndyNemmity]

What is this, LinkedIn?

[jaggederest → AndyNemmity]

Are you permitted to tell us, or just bury the lede? I'd love to hear more specifics if you can.

On: Go is an ideal language for AI-assisted software engineering

[AndyNemmity]

Which exact documents to you give them. The single style guide? The references as well? The additional detail listed in the guide as links?

I'm curious to try your proposal, I just want more specifics.

[AndyNemmity → AndyNemmity]

I've made a pr to my agent trying to implement it. it did fine in blind a/b tests so just going to go forward

https://github.com/notque/vexjoy-agent/pull/908

On: All major LLMs are lib-left. Even Grok, half the time

[AndyNemmity]

Reality has a well known liberal bias

[Vaslo → AndyNemmity]

No it doesn’t. Only entertainers and reporters are - not representative of the US pop whatsoever.

[drcongo → Vaslo]

It's a quote.

[AndyNemmity → Vaslo]

Neither are the politicians.

On: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

[AndyNemmity]

Yep, have been using this for a long time now. No idea why everyone doesn’t.

[al_borland → AndyNemmity]

Does it have any negative impact? If not, I’m not sure why this wouldn’t be the default behavior. It feels like Anthropic is just putting their foot on the scale to drive up costs or for the enterprise, or push consumers to higher subscription tiers.