As always, a very thoughtful and well reasoned take. I read till the end.
I think the Claude Code team itself might be an indicator of where things are headed. We have directional answers for some (not all) of the prompts:
1. We hire mostly generalists. We have a mix of senior engineers and less senior since not all of the things people learned in the past translate to coding with LLMs. As you said, the model can fill in the details. 10x engineers definitely exist, and they often span across multiple areas — product and design, product and business, product and infra (@jarredsumner is a great example of the latter. Yes, he’s blushing).
2. Pretty much 100% of our code is written by Claude Code + Opus 4.5. For me personally it has been 100% for two+ months now, I don’t even make small edits by hand. I shipped 22 PRs yesterday and 27 the day before, each one 100% written by Claude. Some were written from a CLI, some from the iOS app; others on the team code largely with the Claude Code app Slack or with the Desktop app. I think most of the industry will see similar stats in the coming months — it will take more time for some vs others. We will then start seeing similar stats for non-coding computer work also.
3. The code quality problems you listed are real: the model over-complicates things, it leaves dead code around, it doesn’t like to refactor when it should. These will continue improve as the model improves, and our code quality bar will go up even more as a result. My bet is that there will be no slopcopolypse because the model will become better at writing less sloppy code and at fixing existing code issues; I think 4.5 is already quite good at these and it will continue to get better. In the meantime, what helps is also having the model code review its code using a fresh context window; at Anthropic we use claude -p for this on every PR and it catches and fixes many issues.
Overall your ideas very much resonate. Thanks again for sharing. ✌️
I was today years old when I found out Cloudflare has a wall full of lava lamps they feed into a camera as a way to generate randomness to create cryptographic keys
Sílo Twitteru: do dobrých rukou nabízím @zufanek OMFG 2016-2018 + Hvozd II. Dobré ruce se poznají tak, že nabídnou do pátečních 19 hod nejvíc💰, které následně pošlou do sbírky @Pametnaroda na Ukrajinu prostřednictvím @NadaceVia.
RT potěší.
post: We should justify efforts to improve internal quality of software based on its ability to reduce costs of future enhancements. It's a counter-intuitive view, but one that reflects our reality
https://t.co/gFDNbIxwh4
We can reasonably argue about whether Continuous Integration is a good thing or not, but not about the definition of CI. Pushing to master daily has been part of the definition of CI since the term was coined
https://t.co/iWH2ausQVd
Takže, vývojáři, tady je od @spazef0rze, @smitka a @mayermartin seznam toho, co u letos přihlášených webů ještě opravte během těch pár dní, než hodnocení začne: https://t.co/RPHfprMyYV #wt100#metodika
Nepodceňujte u stavby čehokoli roli technického dozora. I když se jedná o zdánlivě malou akci, tak ušetřené nervy a jistota, že vás nikdo nehoupe, za to vždy stojí.
Na zedníky doporučuju https://t.co/BlRwGarf3O a s programátorama jedině @nehoupat :-) #selfpromo
@chemix_cz Je potřeba to brát kontextově. Mít *náborový* banner, který tvoří především *torzo* ženského těla, je vždycky problematické. Je jedno, že to jsou Amatéři. Pokud jsi se ptal, jak dělat naše prostředí inkluzivnější i k ženám (či dalším pohlavím), tohle to imho zrovna nepodporuje.