> It's easy to assume making a word disappear is always the right choice, but you forget it changes the word it leaves behind as well. Very clever.

It's also easy to make the opposite assumption, that the goal is to change the other word. I initially felt weird about changing from a letter at position 3 to the same letter at position 1, but eventually realised that the goal is just to slide the word around, not necessarily to make a new word.

> > you will rewrite huge chunks of your massive codebase

> You're not rewriting Unreal

Do you consider the Unreal engine code to be part of "your codebase"?

It's a dependency .. do you not consider dependencies as part of your codebase?

> That's 1-2% of an annual SE salary for someone with similar skillset.

So commensurate for approximately 2 days of work, a little high for two hours of work, and a little low for 8 days of work.

> A better business would be some kind of product review magazine, where they research products and write articles about them.

Australia has https://www.choice.com.au/ - a subscription non-profit product review website & magazine.

Observational psychometrics over a long enough timeframe (e.g. social media profile lifetimes) probably include periods of challenge or stress, which may help the predictive behaviour.

2024's GPT Store, killed 6 months ago, is back?

https://openai.com/index/introducing-the-gpt-store/

This is a little different since the Apps SDK lets developers create specialized tool calls to their servers, and create specialized in-chat UI components. It's an evolution of the same concept as the GPT store, but a very different take on the idea.

With all the talk of how there must be something to new tech because of the VC money that is being funnelled into it, it's worth revisiting the insane misalignment between VC's incentives and what the rest of us are looking at.

Especially when analysts throw out incredibly optimistic estimates for the future of a technology, the expected value of a 0.1% chance of success in a potential trillion dollar market is a billion dollars, so of course it makes sense to have a stake in that, backed by a properly diversified portfolio.

> 1. First, I use the assistant to come up with the success condition program

> 2. Then I use the assistant to solve the original problem by asking it to check with the success condition program

This sounds a lot like Test-Driven Development. :)

It is the exact same flow. I think a lot of things in programming follow that pattern. The other one I can think of is identifying the commit that introduces a regression: write the test program, git-bisect.

Looks interesting - is there a PEP [0] for this?

[0] https://peps.python.org/

i assume therye trying to build some community before trying to standardise it.

Those terms of service used to be "you should keep your eyes on the road, we are not responsible if you have a crash while playing with your satnav/entertainment system" and "you're responsible for where you drive, so we are not responsible if the satnav tells you to drive off a cliff or into a closed road".

But now that we've trained users that they'll need to click accept on the screen, we can sneak any conditions we want in there about how we collect and use their data...