Is that a pun? Is it so good that I almost missed it? Was it on purpose? I am impressed.

That defeats the purpose then.

If the goal is to say “hi, my local LLM, recommend me a new movie that I like, because god forbid I’ll take a risk and grow”, then you having to curate the data feed going into LLM to describe new movies is in practice this:

• you’ll have to find sources of data (websites, threads, communicties)
• verify each and everyone for poisoning BEFORE adding to your deterministic vectorization (see what Netflix did for recommendation algorithm recently) and applying custom LLM-like in architecture model.

Tl;dr;

Either you can use LLM and will be steered towards greatest quarterly revenue OR you have to put the same effort as if reading all reviews from multiple sources by yourself

And in both cases you still end up with the same outcome “maybe you’ll like it” :P

Either way, you could have your own LLM agent and run it locally

Ignoring everything else, that wouldn’t work. Your local llm instance, to recommend you new movies, would have to scour the internet to summarize information about them.

Boom, thats the vector of it getting steered towards greatest quarterly revenue.

“Enter”.

Or with a flare “Avanti!”.

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.

Okay, the first problem is that the Bible does not say that Nile has 7 tributaries.

It says that (a different river, likely Euphrates), will get smashed into 7.

The second problem is everything else.

You should read their 2026 report - 3x more bugs, 10x code churn, 10% LESS deployments, 50% more epics (my take is smaller epics lol)

There is a MMO with LLM npc chats though? Where winds blow or smthing. They npc chatting sucks.

Or how would you like to use it? Maybe you have some better ideas?

I am running CatchyOs default installation, had not needed to use programming or even cli for antyhing I needed to configure. Everything was clickops.

OpenAi spends 6 billion on marketing. Half of its revenue.

I have never seen a traditional OpenAi ad. But I do see a lot of pseudo viral and bot marketing of it.

You’re a bad staff engineer then if your only criterion is that.

I think you get 20 days until you’re 30 (have 10 years of experience total, university counts)?

Never been to a hotel in the middle of the woods with no other guests

That’s my point. You’re not picking hotel alternative not because airbnb is better, but because there is no alternative.

Booking a cabin

To clarify - booking a cabin (presumably in the middle of the woods, no neighbours?) vs booking a hotel (also in the middle of the woods, no other guests)?

Or does cabin mean something else for you, e. g. any vacation house?