yup, the standard way of thinking about agents seems backwards and probably costly. Use LLMs to write scripts, then stick all your scripts in your own looping harness and call out for LLMs for those parts that are too hard to automate with some deterministic validation at the end.

Can you describe how you work in this higher level? Sounds like scratches a similar itch that traditional programming offers.

Sure; for reference most of what I end up doing is concurrent and distributed systems, so that's more or less what I focus on. I don't know if this stuff translates to other domains.

Basically, when I have an idea for a project, I usually start drawing a diagram for how I think things should work. I usually draw it with draw.io first because it's easy and quick. After that, I usually translate this to Mermaid, primarily just to have a second draft, but also because having a text-based system makes it easy to copy and paste around, and that kind of stuff tends to translates well to state-machine based stuff that most distributed systems tend to morph into.

If what I'm working on is relatively simple, I feed the mermaid code into Claude or Codex, give it some surrounding context text about what I want, and get it to hack away.

For more complicated stuff, especially if I want to be more clever with concurrency, I will take my Mermaid diagram and manually convert it to TLA+. If I get stuck with the TLA+ translation, I will sometimes ask Claude for a bit of help but even then I almost always write 90+% of the TLA+ spec by hand.

After that it's basically the same. I feed the TLA+ spec, and provide context to it as well (e.g. how to translate a manual TLA+ mutex or channel implementation to whatever the language has built in).

Since I focus very heavily on the implementation, Claude and Codex generally don't have a huge issue with doing a one-to-one implementation.

See payolla for the radio era equivalent.

When reading this I immediately thought of them. Anyone I know who plays an instrument said their socials are flooded with them.

Socials being flooded across the board feels weird, but it's also how network effects are _supposed_ to work.

I just hate the fact that I feel jaded and cynical about this as my default position.

Social media is not driven by network effects though. It’s driven by algorithmic engagement and its operation is opaque.

Are they admitting they may be enslaving conscious beings?

Yup, strange to see people still don’t understand LLMs massively speed up coding greenfield pet projects. Anytime you see a bee web app it’s better to assume AI use rather than not anymore.

It actually gives you warning in an overlay first that the favicon would change if you open a new tab. I did and I got "zuckerberg nudes"

The executives are, not the devs.

Yup, and we arr wasting our weekends worried about keeping pace in an imagined red queen's race. Another similar post today.

https://news.ycombinator.com/item?id=47388646

they fantasize about unpaid interns writing specs and nobody ever needed to look at the code in a few years