Sure, they can build “anything”, but the quality is not good. I have recently played a few vibecoded games I found on F-Droid and the implementation sucked.

LLMs could write perfect code in 2 seconds every time and you'll still be on the hook for figuring out what makes something fun to play and nice to use. In fact maybe even more on the hook since you wouldn't get to procrastinate by working so much on impl details.

That depends on the font. If you supply the Latin Modern font with your website, MathML equations will look exactly like in LaTeX.

Ah, I (the article author) am at fault here, for not pointing this out. Things looked fine in my testing because I have the LM font installed on my system.

Somehow we’ve reinvented punch cards, but worse.

It was a companion of punchcards, the tabulating machine. Programming by wires. https://en.wikipedia.org/wiki/Tabulating_machine#Selected_mo...

This is like saying that cars are useless because you can achieve the same thing by removing the cannon from a tank.

I think it's like saying Jev has been trumpeting the invention of a spinning transportation system when we've known such things as a "wheel" for thousands of years. Classification models have been with us far longer than autoregressive LLMs.

Classification models, sure. But classification models that don’t require training data?

The model can spend more “mental energy” on the decision because it doesn’t have to spend any on phrasing the output.

LLMs are constant time per token, if you only let it choose a/b/c/d then there's nothing else it can "spend".

This assumes that you have a powerful computer that can run an LLM. Most people will have to call an LLM API every time, which is three orders of magnitude more expensive than Jev.

most people will, this tongue-in-cheek demo does not though. downloading assets to run a program is not what we refer to when we say "API calls"

You’re still hoping that the model will respect your with to reply with a single letter. With Jev, the model doesn’t even have a concept of replying with something else.

Bocause they expected it to be solved by human mathematicians using techniques that could provide insight into the harder version.

How often do you modify the LLM output before sending it? If it’s less than 50% of the time, it means that by not modifying it, you have added at most one bit of information to what you originally wrote. (If you don’t understand why, think of it this way: Instead of sending the LLM response, you could send the prompt and one extra bit indicating whether the LLM response to the prompt should be modified, followed by the modifications.)

> How often do you modify the LLM output before sending it?

Me specifically, I never send anyone LLM output I haven't give at least a quick read (not skim, read) to make sure it's reasonable and there is no obvious bullshit there. And then I still mention it's LLM-sourced.

> If it’s less than 50% of the time, it means that by not modifying it, you have added at most one bit of information to what you originally wrote. (...) Instead of sending the LLM response, you could send the prompt and one extra bit indicating whether the LLM response to the prompt should be modified, followed by the modifications.

It's not the case, though. Prompts are not interchangeable with output. There is no guarantee that if you send a prompt, and recipient passes it to their LLM, they'll receive anything similar to what you did. It may have mistakes - different mistakes - or just spend focus differently.

The extra bits I claim LLMs can add to the message hinge strictly on you vouching for the response. Of course, you can just prompt an LLM, learn from the response, and then write your message clean, containing both the bits you originally had, and the bits you gained. But at that point, the LLM already gave you text containing all those bits - if you can vouch for it, you may as well copy it over and save yourself the trouble.

> It's not the case, though. Prompts are not interchangeable with output. There is no guarantee that if you send a prompt, and recipient passes it to their LLM, they'll receive anything similar to what you did. It may have mistakes - different mistakes - or just spend focus differently.

I’m not saying that the response is interchangeable, but that due to the data processing inequality, it cannot convey strictly more information than the prompt.

> The extra bits I claim LLMs can add to the message hinge strictly on you vouching for the response.

My argument is that if you vouch at least 50% of the time, the vouching only adds one bit of useful information – either you vouch or not.

> due to the data processing inequality, it cannot convey strictly more information than the prompt.

Only in the case where the LLM message is not reviewed before sending, and only if we assume reliable LLM (so that the receiver could recreate the same output if given the original prompt). This is not a realistic scenario.

> My argument is that if you vouch at least 50% of the time, the vouching only adds one bit of useful information – either you vouch or not.

The alternative to vouching isn't "not vouching", but "correcting and cutting out wrong bits and vouching for the rest", which means the single "vouched for it" adds all the bits that are in final message but weren't there in the prompt.

This doesn’t count because the determination of which house you mean is not based on previous context, but only on the sentence itself.

Do you mean pool?

Yes.