The first time I used a terminal agent was another one.

https://github.com/yieldthought/flow

Happily, 5.5 is good at writing and using it.

Source: spent a couple of years developing an energy and performance profiler for cpus and gpus with various government labs.

I also note that ”for PRs” - will we see these appearing as comments in generated code?

Society is fundamentally counter to individual freedom, and the degree determines the nature of that society and the degree of cooperation possible within it.

The real evil is when someone ensures the famine occurs so they can profit from an outside betting position.

Anonymous trading on prediction markets leads to unpredictable chaos in the end. And as destruction is easier than creation that’s what we will see more of.

Example: a fake German market for train punctuality was announced to make a point recently. If it had been real, train staff and passengers could trivially have profited by betting against any expected punctual train and blocking a door for a few minutes. Or betting against many trains and throwing a hopefully fake body onto a busy line.

Having nice things in society is fragile and not a given. They mostly exist through mutual consent and mild disincentives to destroy the common good. Allow people to profit by destroying them and enough of them will.

If you can’t see that it’s over, I’m not sure what to tell you. You will, in time.

Turned out at their altitude cosmic rays were flipping bits in the top-most machines in the racks, sometimes then penetrating lower and flipping bits in more machines too.

Making someone’s agents 20% better, cheaper or faster will be a measurable and easy sales goal.

Somehow this makes me immediately not care about the project; I expect it to be incomplete vibe-coded filler somehow.

Odd what a strong reaction it invokes already. Like: if the author couldn’t be bothered to write this, why waste time reading it? Not sure I support that, but that’s the feeling.

I've been 5x more productive using codex-cli for weeks. I have no trouble getting it to convert a combination of unusually-structured source code and internal SVGs of execution traces to a custom internal JSON graph format - very clearly out-of-domain tasks compared to their training data. Or mining a large mixed python/C++ codebase including low-level kernels for our RISCV accelerators for ever-more accurate docs, to the level of documenting bugs as known issues that the team ran into the same day.

We are seeing wildly different outcomes from the same tools and I'm really curious about why.

A genuinely interesting and novel approach, I'm very curious how it will perform when scaled up and applied to non-image domains! Where's the best place to follow your work?