Doing an angular -> react refactor with Opus 5 at work.

Amazed at how good it is but also amazed at how dumb it is after I told it I want a very basic and specific code review:do the file names match the contents? is one functionality/concern split in multiple files? do the variable names match what they do? does a method read nicely?

Anyway, I was very surprised at how bad it can be at this.

I suspect it's because the LLM simply does not focus well enough on a single method.

My gut modelling is that the critical files are quite small, some 4k LOC and the LLM tries to read them all in one go and my requirement is surprisingly difficult but the LLM does not realize it, loads all the input into context and simply cannot find a good signal per token/group of tokens.

I guess I can do it because I literally cannot fit 4k LOC in my head and I actually read only tens of lines but I can reeealy dig deep in those lines.

The LLM can remember lots, it has 1M context window, was trained with needle in the haystack problems, but it can severely underestimate how much computation is required with TASTE/universal computation type tasks.

Yes, LLMs are incredible when it comes to delivering well defined outcomes, it's evident they were RL trained very well. But they are incredibly bad at understanding nuance in a text.

It's incredible how agentic coding benchmaxing seems to correlate with writing good poetry but at the same time finding good names for files and variables and wiring beautiful code does not.

Same with getting basic details of who said what in an "adversarial" conversation between 2 humans -- LLMs are incredibly bad at it, with all their "almost discovering new maths" skills

Producing beautiful, coherent, maintainable code. RL trained the models to produce correct code but boy oh boy is it ugly if it's 10k+ LOC

it has to be some amazing router and while the models are open-weights, the knowhow to run them efficiently surely is not?

I presume you can't use deepseek?

There could be structural reason as to why it's not possible, not pumping water *

Some guys in a mediterranean country are drooling right now...

By energy you mean electricity,the nuclear, solar and hydro-- the kind China has installed new 2TW capacity over the last decade while US installed 0.2TW capacity in the same time?

I've been wrong before. However, when was the last time this business model made sense -- that facebook, SpaceX and others, all just pivot from their market niche to general purpose AI datacenter providers.

How on Earth does this make sense?

What happens in a few years when DeepSeek runs on the chinese chips like the Huawei Ascend at a fraction of the cost ?

These are all very high value added companies going into comodity AI hosting and they're all going to make a killing?

This is the kind of thinking that points to that reckoning moment being close.

This and people buying stock with borrowed money*

I mean let's look at bitcoin/crypto.

My experience as IT in modern banks was the opposite. The legal department were absolute assholes when it came to software features. And I'm talking absolutely 100% ok features, like paying your bills from the banking application.

The least fun, trigger happy, cover their buts people I've ever seen.

Like all they could ever say was NO. I guess they were heavily incentivized to just say NO to everything.

I give LLMs snippets of text messages exchanges with my wife and I can't believe how dumb the LLMs are of getting basic facts right let alone nuance.

I'm 100% not one those "LLMs are just stochastic parrots" people, but coding and coding-like activities are extraordinarily well fit for LLMs, but for things that there's less training data, LLMs probably do a lot worse

noob question here from someone who ony played a bit with iceberg and trino: what's the reason to do the analytics stil inside the postgres -- is it so that you don't eat up the IOPS/bandwidth of the main postgresql disks?

I did use pure nicotine and it was very bad for my health, probably due to high dosage, but still.

I've used heavy stimulants, benzos, opioids, dissociatives without an issue, but nicotine is in a class of its own in terms of how insidiously addictive it is.

But just from a health point of view: extreme arm and hand joint issues, forearm vascular issues that made my hands numb at night, palpitations/arrithmia like I was about to die when I used nicotine before sleep and I was drifting to sleep -- it really felt like I was about to die, like my heart was mangled up.

I've said it before: if you allow people to see how much others spent, they will try to climb up the "leaderboard".

It takes just ONE little praise for using tokens or one perk gained, and the GAME IS ON among the developers!

Only if you don't have psychological issues, then none of that really works.

I've done all the sleep hygiene and it does help a bit, but sleep polysomnogram shows my sleep architecture is toast + loads of microawakenings (and no sleep apneea).