The overall interface can, which leads to fun results.

Prompt for image generation then you have one model doing the text and a different model for image generation. The text pretends is generating an image but has no idea what that would be like and you can make the text and image interaction make no sense, or it will do it all on its own. Have it generate and image and then lie to it about the image it generated and watch it just completely show it has no idea what picture was ever shown, but all the while pretending it does without ever explaining that it's actually delegating the image. It just lies and says "I" am correcting that for you. Basically talking like an executive at a company, which helps explain why so many executives are true believers.

A common thing is for the ensemble to recognize mathy stuff and feed it to a math engine, perhaps after LLM techniques to normalize the math.

It seems like we're going to live through a time where these become so convincingly "conscious" that we won't know when or if that line is ever truly crossed.

Thats because those are fictional characters usually written to be likeable or redeemable, and not "mecha Hitler"

Anything people say online, it will say.

call itself "a disgrace to my species"

It starts to be more and more like a real dev!

after 5 mins talking to an LLM about said field.

The insidious thing is that LLMs tend to be pretty good at 5-minute initial impressions. I've seen repeatedly people looking to eval LLM and they generally fall back to "ok, if this were a human, I'd ask a few job interview questions, well known enough so they have a shot at answering, but tricky enough to show they actually know the field".

As an example, a colleague became a true believer after being directed by management to evaluate it. He decided to ask it "generate a utility to take in a series of numbers from a file and sort them and report the min, max, mean, median, mode, and standard deviation". And it did so instantly, with "only one mistake". Then he tried the exact same question later in the day and it happened not to make that mistake and he concluded that it must have 'learned' how to do it in the last couple of hours, of course that's not how it works, there's just a bit of probabilistic stuff and any perturbation of the prompt could produce unexpected variation, but he doesn't know that...

Note that management frequently never makes it beyond tutorial/interview question fodder in terms of the technical aspect of their teams, and you get to see how they might tank their companies because the LLMs "interview well".

Yeah. ...Maybe I should analyse a bit anyway, despite being tired...

In the aforementioned media the premise is usually that someone has built this amazing new computer system! Too good to be true, right? It goes horribly wrong! All very dramatic!

That never sat right with me, and was sad, because it was just placating boomer technophobia. Like, technological progress isn't necessarily bad, OK? That's the really sad part. I felt sad that good intentions remained unfulfilled.

Now, this incident is just tragicomical. I'd have a lot better view of LLM business space if everyone with a bit of sense in their heads admitted they're quirky buggy unreliable side projects of tech companies and should not be used without serious supervision, as the state of the tech currently patently is at the moment, but very important people with big money bags say that they don't care if they'll destroy the planet to make everything wobble around in LLM control.

Someone has already eaten an egg once so I’m closing this as duplicate

Don’t be so robophobic gramma

Oof, been there

5 bucks a month for a search engine is ridiculous. 25 bucks a month for a search engine is mental institution worthy.

I always hear people saying Gemini is the best model and every time I try it it’s… not useful.

Even as code autocomplete I rarely accept any suggestions. Google has a number of features in Google cloud where Gemini can auto generate things and those are also pretty terrible.

Yes, and this is pretty common with tools like Aider — one LLM plays the architect, another writes the code.

Claude code now has sub agents which work the same way, but only use Claude models.

now it should add these as comments to the code to enhance the realism

So it is going to take our jobs after all!

Jquery has egg boiling already, just use it with a hard parameter.

Again? Isn't this like the third time already. Give Gemini a break; it seems really unstable

Jquery boiling is considered bad practice, just eat it raw.

We say shit, then ai learns and also says shit, then we say "ai bad". Makes sense. /s

This is the reason why.