I chuckled in many scenes and more generally with the Hotel California vibes, but the book is also transcendental, mystical and dead serious at times. The mix of it all is what makes it arguably a masterpiece.
In my experience, juniors are absolutely terrified of asking any sort of question at all during a meeting. Senior engineers are far more likely to ask interesting, useful questions.
We hire juniors so that we can offload easy but time-consuming work on them while we focus on more important or more difficult problems. We also expect that juniors will eventually gain the skills to solve the more difficult problems as a result of the experience they gain performing the easy tasks.
If we stop hiring juniors now, then we won't have any good senior engineers in 5-10 years.
I had to warm up a Gemini API project worth a few thousand hours during weeks so that I could get to the tier that allowed me to carry out the workload.
How can you have any tokens if you haven’t finished your tokens?!
As fully-featured as possible, because as much as I like building stuff, I don’t give a shit about coding stuff that has been figured out since the 90’s. Another question is whether semantics and operations get bloated or affect development speed in a framework but I don’t think it’s the case with the Django.
She was largely ineffectual because she was cock-blocked by the ruling classes. I lean libertarian-capitalist and still I think this. Although it's not a settled debate in the classic liberal or libertarian traditions, there are plenty of arguments in them against the excessive concentration of power.
> That's not a problem. That's the system working as intended.
You really think that supra-national legislators regulating the fine-print of unfathomably complex systems manage to have everything working "as intended"?
Why do Draghi or the EC want to roll back this mess then, other than the evident loss of competitiveness respective of the blocs who did not do this? Was that intended or foreseen?
> You really think that supra-national legislators regulating the fine-print of unfathomably complex systems manage to have everything working "as intended"?
For values of, yes. Things obviously aren't perfect, but I at-least generally prefer them over their proposed alternatives. I find they have made things better.
> Why do Draghi or the EC want to roll back this mess then, other than the evident loss of competitiveness respective of the blocs who did not do this? Was that intended or foreseen?
From the article:
> Under intense pressure from industry and the US government,
I think that says what needs to be said. And my opinion is that they shouldn't yield to US government and industry interests, since they clearly aren't the same as European interests.
Draghi's recommendations to roll back regulations had nothing to do with purported special interests, but with his view that regulation was stifling European development. And he's as old guard Euro-establishment as they come.
I mean Europe doesn't really get to make the choices when it comes to the USA because of their hilarious practice of hamstringing themselves. If that was the goal it definitely worked.
I think what they mean is that what EU in general kinda knows that for various they won't be able to make their version of money machine big tech. So why not to try different path? The individual laws will always be flawed because there is huge pressure to make them flawed by corps and lobby that want's to exploit them.
But if you ask anyone in europe on the street they have no sympathy for big tech. If anything they want stronger GDPR and more of it.
The idea of giving it a task that may take six hours and reviewing it also gives me shivers.
I'm a very happy Codex customer, but everything turns to disgusting slop if I don't provide:
(1) Up-to-date AGENTS.md and an excellent prompt
(2) A full file-level API with function signatures, return types and function-level guidance if it's a complex one
(3) Multiple rounds of feedback until the result is finely sculpted
Overall it's very small units of work - one file or two, tops.
I've been letting the above standards go for the last couple of weeks due to crunch and looking at some of the hotspots of slop now lying around has me going all Homelander-face [1] at the sight of them.
Those hotspots are a few hundred lines in the worst cases; I'm definitely not ready to deal with the fallout of any unit of work that takes even more than 20min.
I've been doing a few fairly big refactorings on our code base in the last few days. It does a decent job and I generally don't put a lot of effort in my prompts.
It seems to pick a lot up from my code base. I do have an Agents.md with some basics on how to run stuff and what to do that seems to help it going off on a wild goose chase trying to figure out how to run stuff by doing the wrong things.
I think from first using codex around July to now has been quite a journey where it improved a lot. It actually seems to do well in larger code bases where it has a lot of existing structure and examples of how things are done in that code base. A lot of things it just does without me asking for them just because there's a lot of other code that does it that way.
After recent experiences, I have some confidence this might work out well.
In my experience, for some reason adherence is not even close to 100%. It's fixated on adding asterisk function params in my Python code and I cannot get it to stop... Maybe I haven't found the right wording, or maybe my codebase has grown past a certain size (there are like a dozen AGENTS.md files dancing around).
reply