laksjhdlka

It _is_ performative (not sure it's nonsense) because it doesn't actually do or intend to do anything. It's cheap.

(I personally think it's also _disingenous_, because you can't undo things done 100+ years ago -- not because they are no longer "bad" but because you can't figure out how or who to undo it to, and you should instead focus on "who needs help today", because they are alive).

> Also, optimizing your setup for working with agents can easily make a 5x difference.

Any highlights you can share here? I'm always looking to improve me setup.

Where do you live? I'm in the midwest, US, and theoretical savings between 2x and 5x amounts to a single full bag of groceries. Literally.

How can this possibly be a concern?

Exactly. Somehow the internet has lead to the death of nuance, too many loud voices?

> And the consensus among professional translators is that MTPE only saves time if you're willing to accept a half-assed result.

I have no particular interest in translation, but clearly when the person saying X is bad depends financially on you not buying X, you must take their word with a grain of salt.

They say "if" it's a new work, then it might not be copyrightable, I guess. You suppose that it's still the original work, and hence it's still got that copyright.

I think they are rhetorically asking if your position is correct.

Definitely, in this kind of a scenario the agent is probably best positioned to slog through all that nonsense.

It is not clear to me that keeping prompts/conversations at something like this level of granularity is a _bad_ idea, nor that it's a good one. My initial response is that, while it seems cute, I can't really imagine myself reading it in most cases. Perhaps though you'd end up using it exactly when you're struggling to understand some code, the blame is unclear, the commit message is garbage, and no one remembers which ticket spawned it.

With λProlog in particular I think it probably finds most of its use in specifying and reasoning about systems/languages/logics, e.g. with Abella. I don't think many people are running it in production as an implementation language.

I can't tell which element(s) of the previous post you are criticizing.

I once studied proof theory for a summer at a school in Paris and we talked about type inference and theorem proving all the time in casual conversation, over beers, in the park. It was glorious.

Being a student is so much fun, and we often waste it, or at least don't value it as much as we ought. 20 years later I'd love to go back.

Anthropic has published a very clear statement. It's "no".

And you buy the same brand and model of pants from the same retailer and they still fit completely differently due to variation in the product. Pretty annoying, I just want to buy my Levi's 510s every couple years and get the same thing each time.

How do I add other keys to the little virtual keyboard? Inability to easily type ` is pretty tough. Looks beautiful though.