jondwillis

That’s a decision-shaped comment.

I’ve been considering this as well, and trying to get my colleagues to understand and start doing it. I use it to pretty decent effect in my vibe coded slop side projects.

In the new world of mostly-AI code that is mostly not going to be properly reviewed or understood by humans, having a more and more robust manifestation and enforcement, and regeneration of the specs via the coding harness configuration combined with good old fashioned deterministic checks is one potential answer.

Taken to an extreme, the code doesn’t matter, it’s just another artifact generated by the specs, made manifest through the coding harness configuration and CI. If cost didn’t matter, you could re-generate code from scratch every time the specs/config change, and treat the specs/config as the new thing that you need to understand and maintain.

“Clean room code generation-compiler-thing.”

1) “AI harness plugin build system” to help improve reliability of and increase compatibility across the fragmented AI coding harness plugin ecosystem.

https://github.com/jondwillis/jacq

2) Claude code plugin based on some ideas found in https://www.anthropic.com/research/emotion-concepts-function The main idea is to add hooks that inject “baselines” under some conditions to counteract certain “emotions” that can cause subtle misaligned behavior in agents

https://github.com/jondwillis/functional-emotions

3) Final Fantasy XI custom client remaster in Bevy/Rust alongside an MCP integration that aims to allow agents to play autonomously on private servers à la “Claude plays Pokemon”

Contact: https://jonwillis.dev

No, they don’t. But obviously GP was tongue–—in-–cheek.

We have our doubts about this. Can you share your code or product? Anecdotally, my mistakes and lack of understanding exponentiate the more I try to parallelize.

Congrats on the successful advert

The time to build your community is now, regardless of the threat of apocalypse.

Until they do start doing identity verification, I think you're good. Frankly, don't be a coward. If you're getting treated like this, why would you even want to use their services in the future?

Issue a chargeback.

How’d you get out? For the many over-specialized readers like myself…

I’ve had the exact opposite journey. Native apps, disillusioned and frustrated with the backwards tooling, moved on to more open platforms (web apps and backends)

Why doesn’t he merge them?

I think your repo is cool, but I don’t think creating APIs from web apps is at all precipated on academic research and the other things you mentioned.

Maybe I’m misreading what you’re trying to say.

thanks for chiming in with this noise bot

If there was an infinite App Store, we wouldn't have scarcity and I'd be doing literally anything else other than selling my time for money. I'd also be killed because there's no point to my owners/the world keeping me around anymore in that scenario, except, maybe for my winning personality/companionship.

Oh hey

Would love to chat, I recently wrapped up an initial version of an automated real estate appraisal review app which appears to have some of the same technical challenges and risks. https://getvalara.com / jwillis@valara.net

Would love to share notes. I was able to get away with landing.ai and some really careful schema design and multi-step workflow with a few agents sprinkled in at the end.

Not that much! Not life-changing. It was my first startup, and didn’t know what questions to ask when being hired. I was stupid enough to assume that I would be taken care of. To date, it’s been my only successful exit, and I was granted waaaaay below typical equity for how early I was and how much blood and sweat I gave. This was typical for non-founders and below-directors from what I have ascertained.

Accelerationists gonna accelerate

Literally Pluto TV v1 à la 2013/14.

Source: me. I built it with some folks.

https://getvalara.com - PDF appraisal document in, grounded appraisal review out in 5-10 minutes to aid in risk management for lending institutions and individual appraisal reviewers.

We use landing.ai to parse the PDF, as well as useworkflow.dev to durably perform other work such as rendering PDF pages for citations, and coordinating a few lightweight agents and deterministic checks that flag for inconsistencies, rule violations, bias, verify appraiser credentials, etc. etc. Everything is grounded in the input document so it makes it pretty fast and easy. We’re going to market soon and have an approval sign up gate currently. Plenty of new features and more rigorous checks planned to bring us to and exceed parity with competition and human reviewers.

There’s plenty of margin for cost and latency versus manual human review, which takes an hour or more and costs $100 or more.

Getting tons of Gell-Mann from this one. On the surface level, a more rigid type system helps, but it doesn't remove all potential classes of bugs. For example, if you're using Rust to interact with LLM APIs, you're still sending strings around. If those prompt string reference code such as a field name as a string literal, and you rename the field name, but forget to update the string, you've got a bug. You can, of course not use a string literal, but hey, it happens. I'm not sure if Rust can reference field names at compile time and get them into string, but I do know TypeScript can.

Which brings me to... choosing to throw TypeScript under the bus for having an "unsound" type system ignores the fact that you can just throw more tooling at the problem (e.g., a linter that disallows `any`, since that one example cited in the article), and glazes over the fact that the JS ecosystem has a lot more examples in the training data for many LLMs. The further you deviate from the slop-mean, the worse time you're going to have using LLMs to generate code, slop or otherwise.

> AI-enabled mass surveillance is fine as long as it isn’t domestic.

> We want AI to be aligned with all of humanity.

One of many contradictions. Liars.

Always, eh?

I initially didn’t read this post, fixated on “company event”, and thought it could be used for a single-day, one-off “thing to do tonight given (location) and (preferred activities/venue type) after (work end time)” It presented hotels and then some potential activities, but didn’t look up the time. When I asked about what is open after the time, the agent seemed to realize my request was not in your typical use case flow and gave me a refusal.

It’d be cool to offer one-off event suggestions, but I understand that’s probably not as easily monetizable.

And we won’t. Uber Eats Burger Reich and all.

Oof

Will you provide context around how you got involved and got your neighbors to vocalize? I think there’s a lot of learned helplessness and cynicism that gets in the way of making things better. I know I personally suffer from this and lack the tools, motivation, and follow-through to make an impact.

I went to a meditation garden yesterday and noticed their signage was much more nonviolent and “together” inducing than most, without coming across as too woowoo:

Next to a Koi pond: “Will you help protect these beautiful fish? Help us by not throwing coins, food, …”

It’ll probably be fine. Mostly.