IMO Sonnet 4.5 is great but it just isn’t as comprehensive of a thinker. I love Anthropic and primarily use CC day to day but for any tricky problems or “high stakes, this must not have bugs” issues, I turn to Codex. I do find if you let Codex run on it its own too long it will produce comparably sloppy or lacking-in-vision type issues that people criticize Sonnet for, however.
Sonnet 4.5/CC is faster, more direct, and is generally better at following my intent rather than the letter of my prompt. A large chunk of my tasks are not "solve this concurrency bug" or "write this entire feature" but rather "CLI ops", merging commits, running a linter, deploying a service, etc. I almost use it like it was my shell.
Also while not quite as smart, it's a better pair programmer. If I'm feeling out a new feature and am not sure how exactly it should work yet, I prefer to work with Sonnet 4.5 on it. It typically gives me more practical and realistic suggestions for my codebase. I've noticed that GPT-5 can jump right into very sophisticated solutions that, while correct, are probably not appropriate.
Sonnet 4.5: "Why don't we just poll at an interval with exponential backoff?"
GPT-5: "The correct solution is to include the data in the event stream...let us begin by refactoring the event system to support this..."
That said, if I do want to refactor the event system, I definitely want to use Codex for that.
Strangely enough this is one of the first times here I see someone with the exact same experience. GPT-5 is very prone to a style that would for most codebases be overengineering. I think as a large part of HN works on huge enterprise FAANG-like code, this is where it shines, so here it gets rave reviews of just being the best overall. But globally, for most developers, it's overengineering and adds a lot of unnecessary code to maintain. Sonnet in that sense remains "every man's coder". I've gone back from 4.5 to 4 now, having spent a good chunk of time with 4.5 it just seems like a slight overall regression with no real upsides besides being a little faster than 4.
Glad I'm not crazy, the tide right now of codex > sonnet is overwhelming. Frankly I think what most people go by is "does the code work" - codex is admittedly relentless. It's very good at producing code that works. But "does it work" is not the end-all-be-all in most cases...
I frequently have multiple coding assistants going at once—Gemini 2.5 Pro via Aider as the workhorse for most standard changes, Sonnet 4.5 via Claude Code for question answering, documentation, test case development, or broad based changes to many files in a project, then GPT-5 for more complex diagnostic or architectural type things—I don’t generally like the code it writes, but it will often be able to fix situations where the other models get stuck in some kind of local maxima.
Even inside the claude-code ecosystem, more than ever there are tradeoffs on raw speed vs intelligence vs cost.
Moving a bunch of verbose templated HTML around while watching results on a devserver? Haiku all day. It's a bonus that it's cheaper, but the real treat is its speed.
Adding a feature whose planning will involve intake of several files? Sonnet.
Working specifically on 'copy' or taste issues? Still I tend to prefer Opus here.
I'm like 80% sure Sonnet 4.5 is just rebranded Opus.
Sonnet 4 was a coding companion, I could see what it was doing and it did what I asked.
Sonnet 4.5 is like Opus, it generates massive amounts of "helper scripts" and "bootstrap scripts" and all kinds of useless markdown documentation files even for the tinies PoC scripts.
I have a very similar experience. I was heavily invested in Anthropic/Claude Code, and even after Sonnet 4.5, I'm finding that Codex is performing much better for my game development project.
“Parent-led homeschooling is the approach that puts parents in charge of the education decisions for their children.”
Teachers in the US are required to have a Master’s level education and multiple months of student teaching in order to be certified to teach. Yes, there are many kids in the classroom. Yes, your kid isn’t going to get the same type of 1 on 1 attention you can give them at home. However, work in conjunction with the experts, don’t presume you know better by default.
> Teachers in the US are required to have a Master’s level education and multiple months of student teaching in order to be certified to teach.
There is no federal teacher licensing standard, and state standards vary (and only apply to public school teachers, IIRC). In several states, the only educational requirement is a bachelor's degree. [1] This educational requirement might be coupled with required teaching experience, but this experience can be gained by teaching in a private school, where such requirements do not apply. And none of these experiential requirements establish a baseline for excellence — they just measure based on "time served".
It is simply false to assume that all teachers are "experts" to whom parents (who may have many more years of education, not that formal education is the touchstone), should defer.
The article (appropriately) glosses over a fun butterfly effect. The large export of lemons to Britain is a core reason for the existence of the Italian mafia.
What makes Europe unique such that the proposition that lowered taxes would lead to greater Millenial success holds true, when the same low-tax policies applied in America seem to have yielded similar results to the European approach? If this seems like a leading question, it's not intended to be--I'm American and curious about the potential variables at play here that I'm not aware of.
the European market is a disaster for investment and entrepreneurship, that's what's holding millennial back. your average SMB reach is often regional, and the bureaucracy structure makes almost impossible for garage operations not only to go above national, but to even exist.
like in sports, the size of the talent pool matters, and with an unbearable cost for entry entrepreneurship almost s losing proposition unless if under the heels of some financing partner whims, as it's the only realistic option to sustain the bottom line costs from handling vatmoss, letters of taxations and the other billion historical bureaucratic commitments
Yep, close to half my company was laid off at the beginning of the summer. It was hard, it had been clear the company didn’t have the revenue to keep running but we were constantly assured the current round of funding would close. Then it didn’t and a lot of us were gone
Salaries at FAANGs are hard. I received an offer (New England based) for an L6 position from one this week and was shocked at the package. After getting off the phone and doing more research, I realized there's a chance I'm being lowballed, and I should negotiate for more if I choose to go to said company. I've done pretty well in my career so far, but even taking the initial offer would almost double my salary.
