Pointing out the architectural reality of how these APIs actually execute isn’t trolling

Cool. Except that you didn’t do that before. You’re doing that now, after the fact.

Prove it then… 99% of people like you never actually want to have a real technical discussion, because you spread your opinions based on feelings and not facts.

This is extremely funny that you’re trying to insult me, based on your feelings and not facts.

My only participation in this thread was that UBO Lite creator disagrees with you, which he publicly stated, but you felt… Offended? (No idea) - and decided to insult me rather than to deal with facts.

There is a word for people like you.

Troll.

Literally, the creator of UBO Lite disagrees with you.

Why are you like this?

when it can do something that is not just automating a simple task, but it’s capable of doing things that humans are no

No, credit when credit’s due, LLMs have arrived (by themselves) or helped to arrive at some mathematical conclusions, didn’t they?

A few of Erdős, some others.

Yes, it’s, a very small subset (duh), out of god knows how many they tried, and achieving the solution is made via technique called “infinite monkeys typing out Hamlet”, but credit when credit’s due (unlike LLMs that don’t properly attribute parts of the proofs).

Them

LLMs do not change

You

Not with agents and chain of thought. Agents can run for hours continuously

Those are not the same concepts. The model of LLM remain unchanged. Agents running for hours just modify the prompt they input into an LLM model.

I do not care about the rest of discussion, just swoop in to clarify that distinction.

I hate AI too

? Never said that.

Anthropic claims that Mythos has low low low hallucination rate of just 40% in its System Card.

LLMs outputting code solving this exact task is a compound function of luck, with non determined a priori chance of success and unknown a priori cost.

This is my main disappointment with agentic coding. Prompting is fine, quality assurance is there from the start. Greenfield, couldn’t care less. Established enterprise code? This is a minefield.

If the tokens were 10 to 100 times cheaper, then it would be a maybe.

I also hate how it makes half of my senior engineers dumber.

1. Why would you use shit for comparisons? Compare upwards. And why would you inject US into this thread too?
2. I don’t care about this thread or you, why would I spent more effort showing more metrics?

You forgot, you have to ignore all the good things China does

For it’s workers? China is still behind EU when it comes to workers rights and benefits though? Good for them they are slowly, very slowly progressing in that regard.

E.g. paid time off in China is 5 days a year, +5 for every decade of cumulative work experience; it starts at 4-6 weeks in the EU; China has more of it’s own youth muddled in gig economy then EU (don’t get me started on how exploitative gig work is, it is disgusting any country allows for that practice).