This post is not about Navier-Stokes. That is in a different thread. Glad you're cry-happy though.

Wait, is NS solved? I thought I was just a singularity thing?

There is an announcement by OpenAI https://news.ycombinator.com/item?id=49613262

Climate change, most likely.

Agreed. Opus 5 is doing just fine, slightly better than 4.8. It's personality is insufferable, but I find myself catching fewer problems at code review. It generally understands my conventions and isn't so eager to accrue tech debt.

Both. Command the author to use the style, then command a reviewer to check it. Write one skill called review-prose with your rules, and another called write prose which tells the author they will be judged by review-prose, so you only write the rules once.

What I have found is that getting a model to rewrite a badly written passage is hard, because it seems to key off what it reads. It might swap some vocabulary around ok, but it doesn't fix structures very well. So getting it close to the preferred style in the first place is better.

To take this further, if you must fix existing bad prose, write a clean-prose skill which extracts the bare structure of the prose with none of the style, hands it to an author subagent who isn't poisoned with the original bad prose, then hands the output to a reviewer subagent.

Opus 5 writing is horrendous, so I have been experimenting with improving the output!

_Exactly_.

Both the article and the parent comment treat "happens to have Kik account" as an independent discovery that affects our Bayesian inference.

No. The innocent was identified exactly _because_ they have a Kik account, so the conditional probability they have a Kik account is 1.

No. If the target of your "Bayesian inference" is whether the chain kik->gmail->ISP is reliable, then it isn't independent evidence. But that isn't the same as the target of inference in court, which is guilt or innocence, and obviously having kik is additional evidence for that. As I mentioned, the chain kik->gmail->ISP would not even be disputed in a run-of-the-mill accusation in the US, any more than DNA evidence gets scrutinized for lab mix-ups. You would need expensive attorneys and experts for that.

What you're describing is very close to what education theory calls "assimilation" and "accommodation". When we assimilate knowledge, it just fits into our schema of understanding. When we accommodate knowledge, we need to change our schema, and that is where the feeling of being challenged (and often the feeling of profundity) comes from.

For example, a child learns that "foreigner" means someone from outside their country. Then, when they're 11, they go on their first holiday abroad and realise "Wait! _I_ am a foreigner here!"

So, maybe one way to frame what you're saying, is that LLM output tends towards being easily assimilable.

The article presents hypothesis as fact with insufficient science. I have no problem discussing speculation, but if the author wants to promote their claims to any more than that I would want to see more journalism.

What journalism would you like to see in a blog post about the authors opinion?

I completely agree with this you. The article is NOT about product ideas. Your parent has misunderstood the article.

This is pretty unfair. If the author didn't establish some context there would be someone else here saying "Check out this dilettante telling me what to think."

I have a degree in mathematics followed by twenty years in software development (pillory me, if you like). My conclusions after 6 months of using LLMs every day are remarkably similar to the author's. I increasingly think in shapes, architectures, data structures and ideas; less and less in lines of code.

And I fully understand his point that, once the architecture of an idea is settled, reading LLM code does not feel worse than reading human generated code. Especially if you have a strong style and conventions guide.

The idea is the hard part, and it's the right place to focus your effort.

I bet you had to solve math equations and prove math stuff to get your degree, am I right? Now imagine I tell you that you could have just prompted LLMs with “please solve the is and make no mistakes”, would you think you’d be able to get your math degree?

The point I’m trying to make is that it’s very easy to tell everyone “don’t read the code, just focus on architecture” when you have decades of experience behind your shoulders, where you HAD to read the code, iterate, learn from your mistakes, read code written by others, and actually writing and making stuff yourself to gain that experience and understand architecture.

How do you expect people to learn all this stuff that you know if don’t want them to actually do the work but instead “control the idea”, whatever this means? It’s just baffles me that people don’t see this.

I see it. I'm with you. It does feel lonely though, doesn't it?

You made my evening a bit better by your message, kind stranger. It is lonely in there, but I suspect you know, just like me, that we can't chose a different path.

Neat! I think agents making Word docs and PowerPoints is going to go away. I think something like small docs is the future.

I don't think the corporate world is moving away from Word and PowerPoint anytime soon.

Thanks very much! That is exactly my view too.

It’s also nice to get out of the command line for doing deep reading.

I have had a few developers try it, and some small number of them use it week after week (as do I): https://smalldocs.org/analytics