sunir

I'm building a high level code explorer, like the CASE systems of a long time ago I suppose. I also built a facility called zork that lets me and an agent explore the code system together like a dungeon, taking notes as I go and if you want to take the metaphor too far, 'invoking spells' or rather commands like code references, call flow, data flow, exception flow, profiling, labelling design patterns and validating implementation, etc.

With zork I can also just start typing in a code file and leave instructions for the agent to fill in or fix parts of the code while I'm editing it. So I can lay out what I want the class shape to be and don't have to implement all the annoying little parts. This feels more like the GitHub Copilot days.

I honestly believe more of us will pair program with agents, not just yelling at a chat window.

I didn't say that. I just pointed out that computers are better at these mental activities than humans, and humans still do them. More in fact.

Academic mathematics isn't an operational institution.

Though its funding does move with the number of major projects academia is tasked with that rely on mathematics to advance, it's a fundamental knowledge area that has no operational requirements to exist.

People still play chess and go and StarCraft. People do what people want to do. It's not clear whether this will reduce the number of working mathematicians or increase it. There will a lot to learn from the machine proofs that will open up new frontiers as well.

So, it's like the story, "We'll see."

There has been a shocking but not altogether surprising development, and all reactions are valid.

sudo pmset disablesleep 1

Your Mac will now work while the lid is closed.

I predict we are less than 12 months away from the pendulum swinging back to hand coding but dragging ai pair programming into the workflow. This is why I don’t worry too much about this.

I can predict this because I’m building such a thing for myself as are many others. It seems to be where the tao of slop is going.

Here's a good set of questions for any write up:

Who are we talking about? What's their role? (What agent? What is the job to be done?)

What is the status quo? What's the problem with the status quo? What else has been tried? What's the consequence of not solving the problem? What more important problem do you need to work on that you're blocked because of this problem? What's the ideal solution? What's the current offer? Why would someone say no to any given solution? How have you addressed those problems?

When I was younger, I was in Berlin and wandered unannounced into the Chaos Computer Club and I met Tim there. What a legend.

The whole club is legendary. We need more of their spirit of the art of the possible and irreverent. Life is for the living, and computers are for the hackers.

Yes. I have so many stats texts and like many technical fields I suspect they are written as if we learn how things were derived historically not how they truly are.

It’s more likely that they have llms supervising llms in training and therefore the quality has dropped like a picture of a photograph.

If opus has high signal thinking it would be able to write a fsm but it’s been a month of me trying whereas Luna can do it in a few minutes.

I think it is similarly that they are using too much synthetic data.. meaning they are feeding the models the transcripts of users where many users have figured out to let agents just message each other.

Again picture of a photograph.

I'm still traumatized from Space Quest I because I didn't grab a broken glass from the windshield of our crashed spaceship before entering the cave with the laser.

It's been 40 years. I vote wkfauna for President.

From a computer science point of view, it's the same argument as why NP-complete problems are hard to solve, and easy to check.

From a practical point of view, however, it's the same argument we write unit and integration tests. We accept error rates in the program under test, the test, the test harness, the programming language, the operating system, the hardware, and the universe. The goal is reduce the error rates enough you can ship something you can get paid for and won't get sued for later before you starve to death.

Try the left arrow in Claude Code and now you have session search. Or claude --resume, down arrow, then Ctrl-A to see everything