Nothing about this post ever gave me the smallest hint that this was any way related to a kid exploring computing world.

It doesn't sound malicious, it was malicious on purpose and it was a good thing.

If anything, the original operator should be happy to have been hit with a $ 1'800 lesson and not a $ 180'000 one.

Sure it's better at vibecoding whole tasks, it's clearly good at it, but give it a simple one, and it will still do way more than needed.

It's way too fixated on validating even the simplest things, I find it an unproductive model unless you're implementing whole tasks and doing other things in the meantime.

This so much.

Opus 4.6 was the last Anthropic model that was good at assisting you, 4.7 and later ones have completely inverted this relationship and it's you assisting it.

Yes, I admit they are smarter, I admit we've reached a point where LLMs are more creative and could be writing better code (albeit with some design hiccups) than I do, but they are also increasingly bad at helping me.

Sure, they do my job when prompted 8 times out of 10 (but then, what's the point of having me anyway?), but my issue is that when I try to invert the relationship they will keep jumping onto solving the issues themselves and disregard my feedback or request.

E.g. I wanted to know some DNS details of an emailer module in Fable 5 and it jumped onto "why I should've used magic links", it just not did what asked.

E.g. 2. There was a worker machine that had an environment misconfiguration and I tasked it to find which github action was setting that specific flag and where. Instead of answering a question, it jumped into just hardcoding it in the code.

E.g. 3. I had some issues with batching, and while I tasked it to investigate whether batching was needed at all for that particular problem (hint, it wasn't) it went and changed the batching logic as to fix the bug.

I am extremely disappointed with Fable's personality.

I can clearly see it's strong, but I'm wondering whether the relationship of LLMs as assistant has broken forever, and it's us now that are being tasked into assisting them instead, because that's how it feels.

The training/reinforcement is clearly biased towards solving problems, not answering questions.

I haven't stated that it's not more capable nor more "intelligent", it's the opposite.

I will try to expand on what I mean.

LLMs "character/persona/tendencies" are increasingly less about acting as an assistant and more about finding the solution itself.

I use AI in a specific way: he assists, investigates and answers my question. I do the coding. It is increasingly difficult to use it as such, because it quickly jumps into giving me solutions instead of answering my specific questions.

I'll give you few examples.

I asked it to investigate DNS handling details in phoenix emailer module work, he did very little investigation and jumped into why I should've used magic links instead. Instead of assisting me in my research, it was hard wired to solve the problem (the wrong one, with a very wrong solution).

Today at work, I had a problem with batching, I wanted to understand if batching was even needed at all for our use case, and he kept circling around how to fix the batching bug instead. That's not what I asked it to do, yet, it jumped to the "solution".

I am increasingly frustrated by these models "personality" and tendencies that are unhelpful to assist me doing the task at hand and more on it doing it and me merely assisting/supervising.

Sure, very detailed prompting on how he has to act helps, but wait few turns and he drifts again to his default solution vomiting state.

Which makes me think that these models are hard wired on this mode of operation by consistent training and reinforcement of jumping from prompt to code solution.

AI should be assisting us, instead it's doing the job and it's us being an assistant to it. This is a monumental shift that people seem to be missing in how knowledge working is changing and it's going beyond mere coding.

Guardrails, prompts, whatever, it's us helping it doing the job, not the other way around.

Opus 4.6 was the last genuinely good assistant LLM, but since then it's quite clear that the training/reinforcement is focused "given prompt -> do task" so it's behavior is more and more about doing it itself, not helping you. If you try to use it as an assistant it just sucks and is perma wired into finding the solution. Many times I want it to help me investigate, and his answer will still be focused on the fix, not answering my questions.

4.7 first, 4.8 later and fable are absolute disasters as assistants.

Fable in particular is so "intelligent" that it will push with very strong and intelligent takes even if it is completely wrong.

I have never disliked our job more.

And yes, it's an excellent model.

In any case that's what closed source (weights) for the masses means.

Local inference has never been so important as it is now.

From Opus 4.7 onwards each following model is becoming less useful as an assistant and turning you as the assistant.

But I guess that's normal when it's trained to pass benchmarks end to end.

In fact it has become extremely good at pushing against feedback with extremely convincing and intelligent takes, even when it's completely wrong.

I have extensively tested it against Opus 4.8, gpt 5.5 and there's still many coding tasks gpt 5 is better. But vibe coding?

Sure, it's definitely slightly ahead, even compared to gpt 5.5 pro (through api, not pro plan).

And don't dare to contradict me, the fact that MIT-bred leetcode ninjas paid half a million per year can't produce a simple (mostly static) website on that stack it's only because of management that wants to ship the next product. /s

I *don't* want to have to know what others are doing nor how. This may work on teams that work on a narrower scope and lower rhythms, cannot work for us.

Is Mercedes stupid?

How did Carl Benz dare to do something as hideously complicated as building the first gasoline-powered car in history?

And why did they kept inventing complicated stuff that ended in all modern cars like ABS, adaptive cruise control, direct fuel injection, emergency brake assist, etc, etc?

At least I don't have to review PRs, we have built a team around the concept of trust and not needing to check each other's work.

There's simply too much work to start nit picking in PRs, everybody's very talented and a good engineer you can trust. They ask for feedback when they want it.

And no, we're not producing slop, if anything AI has helped improve the codebase a lot and the harnessing has definitely raised the bar at all levels.

But sure as hell, the job sucks now, and I hate it. And it's not just due to the amount of work.

I haven't been on the market for long luckily, but as an independent consultant I went from getting 2 to 3 contacts per week to none per months.