noosphr

I imagine it has been, but they didn't release it because the diff is too big to be accepted into regular Python and it would cost more to fix it than use it as is.

With the current sota models code is free.

You set the agents against themselves and burn tokens like there's no tomorrow.

The feeling of coding like that is a bit like realizing that an elevator is 10cm of aluminum and a 100 meters of empty space under your feet.

After the first few bouts of existential dread you get uses to it.

[[citation needed]]

I believe that the current generation of AI models have matched the hype of the last few years after the previous generation did not.

Whether they will keep doing so is another matter entirely.

The train will keep going for another 6 months at least.

You can easily read posts before 1994, what you're saying definitely did not happen.

At the start moderators worked with you, after 2014 they worked against you.

They still do, it's just that the first 95% of carving things out of rock is literally getting the rock into the shape needed to start doing actual scuplting.

I'm short, it's artistic boilerate with no meaningful value to either the artist or the viewer.

There is more code than ever. The amount of software seems to be shrinking.

The second iPhone was the 3g the third was the 3gs.

Trying to review slop code by eye is as productive as using pencil and paper to check address arithmetic in assembly from a compiler.

The fake main points can be excused since the underlying models are auto regressive and that's as good as you can do with a regular language.

LLMs text generation is much closer to the way humans speak than to the way good writers write.

AI generated text has no human centered underlying model of physical reality and its metaphors are tortured as a result.

If we had talking centipedes the results would probably be similar, but for different reasons.

Or $10 on open router.

>I'm sitting here watching astra do in a day what would have taken me at least 3-6 months.

I've got some bad news for you.