Given that guidance, I tried specifying "Unless I ask you to elaborate, respond with no more than one paragraph, using sentences of 20 words or fewer." It works...ish. I still see it violate this rule regularly, but it's less bad IME.
523 karma · joined January 28, 2011
CTO at Config (https://config.com)
Personal website: https://krieger.io
[ my public key: https://keybase.io/cjk; my proof: https://keybase.io/cjk/sigs/ItSjdGcDzRZHDPvBRf-EIRP4QOJEdA26KPBHvi7f3Nk ]
Given that guidance, I tried specifying "Unless I ask you to elaborate, respond with no more than one paragraph, using sentences of 20 words or fewer." It works...ish. I still see it violate this rule regularly, but it's less bad IME.
In my case, I have a semi-autonomous loop where Claude writes some code, and uses `codex exec` to do an adversarial review. I had what should have been a trivial feature go for 13 rounds of review/fix before I stopped it, where each round was just flip-flopping the same logic back and forth to try to make the tests pass. Codex kept (correctly) re-identifying the issues Claude was flip-flopping on. Codex even suggested fixes that would have worked; Claude ignored them repeatedly. I never saw anything remotely this bad on Opus 4.8.
Additionally, I have a CLAUDE.md instruction to not silently defer anything, and ask me anytime it wants to do so. Opus 4.8 paid attention to this rule the overwhelming majority of the time. Opus 5 seemingly cannot be bothered.
I have tried updating my CLAUDE.md according to Anthropic’s recommendations for Opus 5, but it doesn’t seem to have made any difference.
It takes five minutes of trawling through the videos on the GDC Vault to see all of the clever and interesting ways modern graphics engineers are eking every bit of performance out of modern hardware. Is it as clever or innovative as Carmack's fast inverse square root? I don't know. I'm not sure how to compare those things. But there is still plenty of room for that flavor of work for those that are interested.
It sounds like you're fairly new to programming, so I would suggest a static site generator that is easy to install and use.
Zola[1] is less well-known, but it's easy to install and fast. I tend to use Hugo[2] the most these days, which is fast and has solid documentation, but its template syntax is really annoying compared to Zola.
[1]: https://www.getzola.org/documentation/getting-started/overvi...
If you’re not interested in hand-maintaining the code of the website(s), and you just want a nice GUI for publishing pages/posts/etc., then I’d say use some hosted platform like Squarespace.
For actually learning how to build websites, start with something more low-level and barebones like a static site generator (Jekyll, Hugo, Gatsby, etc.), or even plain GitHub Pages without a static site generator for the most “manual” experience.
In neither of those cases would I consider WordPress.
(That is not to say that the FCC change will move the needle on the underlying issue of router security; as some of the ancestor comments have said, lax security practices are common industry-wide, irrespective of country of development/manufacture.)
The car saw this dude coming from way down the street, flying, and was like “yeah, better stop.” Probably saved the biker from serious injury, or worse. I wouldn't have seen him if I was driving.
Where'd you see they're exiting pro/flagship tier stuff? Everything I can find says they're continuing to hand-make their higher-end stuff in Germany. One such source: https://www.whathifi.com/headphones/100-year-old-headphone-b...
Glad to see them setting a great example here instead of letting these speakers become expensive paperweights.
I worry that we are edging closer and closer to a similar phenomenon with macOS as well. Apple seems intent on squandering every bit of stability and sanity that macOS used to represent. Maybe now that Alan Dye is gone, we will at least see the abomination that is Liquid Glass fixed…somehow.
For boilerplate stuff like generating tests against a well-defined API, in a compiled language, maybe 2-3x. Far less in languages and frameworks like Ruby/Rails where the distance between generating the code and figuring out if it’s even valid or not is large.
Mechanical refactors that are hard to express via e.g. regex but easy in natural language: maybe 5x.
HTML and CSS, where I know exactly what I want and can clearly articulate it: 2-5x.
For anything architecture-y, off the beaten path, or where generating a substantial amount of code is required: near 0%. Often in the negatives.