Quality of that verification matters, people who might use AI tend to cut corners. This does not completely solve problem with AI slop imo and solution quality. You ask Claude Code to go and implement a new feature in a complex code base, it will, the code might even work, but implementation might have subtle issues and might be missing the broader vision of the repo.
I was trying to find some more context on this but all I could find is that Rob Pike seems to care a lot about efficiency of software/hardware and against bloat which is expressed in his work on Golang and in related talks about it.
I was also surprised by that. It is relatively cheap to measure as you can just buy BP monitor and do it yourself at home. Considering that high BP is very often asymptomatic, I, for example, even feel better with high BP, many people walking around accumulating damage for years. Not to mention it also goes with a baggage of other side-effects like increased chances of a stroke and kidney failure.
For some reason it hits differently when you go eat something salty or drink coffee or get all stressed out for now reason and then see increased BP with your own eyes. That was what motivated me to stick to a better diet, cut caffeine and chill out.
Also started to suspect that, but I have a bigger problem with the content than styling:
> "Instead of remembering complex Kubernetes commands, they ask Claude for the correct syntax, like "how to get all pods or deployment status," and receive the exact commands needed for their infrastructure work."
Duh, you can ask LLM tech questions and stuff. What is the point of putting something like that on the tech blog of the company which supposed to be working on beading edge tech.
To get more people using it, and more. I’ve encountered people who don’t use it because they think that it isn’t something that will help them, even in tech. Showing how different groups find value in it might get people in those same positions using it.
Even with people who do use it, they might thinking about it narrowly. They use it for code generation, but might not think to use it for simplified man pages.
Of course there are people who are the exact opposite and use it for every last thing they do. And maybe from this they learn how to better approach their prompts.
I think Altman said in Lex F. podcast that he works 8 hours, 4 first one being the most productive ones and he doesn't believe CEO claiming they work 16 hours a day. Weird contrast to what described in the article. This confirms my theory that there are two types of people in startups: founders and everybody else, the former are there to potentially make a lot of money, and the later are there to learn and leave.
What I really wanted to know if OpenAI(and other labs for that matter) actually use their own products and not just casually but make LLM a core of how they operate. For example: using LLM for coding in prod, training/fine-tuning internal models for aligning on the latest updates, finding answer etc. Do they put their money where their mouth is, do LLMs help with productivity? There is no mention of it in the article, so I guess they don't?
I don’t know, but I’d guess they are using them heavily, though in a piecemeal fashion.
As impressive as LLMs can be at one-shotting certain kinds of tasks, working in a sprawling production codebase like the one described with tight performance constraints, subtle interdependencies, cross-cutting architectural concerns, etc. still requires a human driving most of the time. LLMs help a lot for this kind of work, but the human is either carefully assimilating their output or carefully choosing spots where (with detailed prompts) they can generate usable code directly.
Again, just a guess, but this my impression of how experienced engineers (including myself) are using LLMs in big/nontrivial codebases, and I’ve seen no indication that engineering processes at the labs are much different from the wider industry.
Quality of that verification matters, people who might use AI tend to cut corners. This does not completely solve problem with AI slop imo and solution quality. You ask Claude Code to go and implement a new feature in a complex code base, it will, the code might even work, but implementation might have subtle issues and might be missing the broader vision of the repo.