Every time I've tried to actually use gpt-oss 20b it's just gotten stuck in weird feedback loops reminiscent of the time when HAL got shut down back in the year 2001. And these are very simple tests e.g. I try and get it to check today's date from the time tool to get more recent search results from the arxiv tool.
Not really an apples to apples comparison. You are comparing it to core technologies that millions of things sit on. There will always be money for that.
Its almost never correct to rip on a project from a distance. Only two things can happen, one, you are wrong, and the project succeeds. This is a personal catastrophe for your career at that company. Two, you are correct and the project fails. Its rare this will get you enough credibility to make the risk worth it. There are always others that will show up and dogpile as if they "knew" the entire time themselves. You need to be consistently correct about failure to get truly noticed, but then it asks a lot of questions. Why are you still working there? Why don't you have enough influence to prevent it in the first place? "I told you so" rarely accomplishes anything good.
Cool project, but I never found the cloudflare DX desirable compared to self hosted alternatives. A plain old node server in a docker container was much easier to manage, use and is scalable. Cloudflare's system was just a hoop that you needed to jump through to get to the other nice to haves in their cloud.
this, provided you don't mind hopping around a lot, 5 20 dollar a month accounts will get you way more tokens typically, also good free models will show up from time to time on openrouter
If your outlook is 10 years then for sure, its valid. I am not sure how you come to that conclusion logically though. At the beginning of the year we had 0 code agents. Now we have dozens, some are basically free, (of various degrees of quality, sure).
The last 2-3 months of releases have been an unprecedented whirlwind. Code writing will be solved by the end of 2026. Architecture, maybe not, but formatting issues isn't architecture.
Nope, it was solved with Visual Basic in 1991. And with Nextstep in 1989. And with...
I really dislike people comparing GenAI with compilers. Compilers largely do mechanic transformations, they do almost 0 logic changes (and if they do, they're bugs).
We are in an industry that's great at throwing (developing) and really bad at catching (QA) and we've just invented the machine gun. For some reason people expect the machine gun to be great at catching, or worse, they expect to just throw things continuously and have things working as before.
There is a lot of software for which bugs (especially data handling bugs) don't meaningfully affect its users. BUT there isn't a lot of software we use daily and rely on for which that's the case.
I know that GenAI can help with QA, but I don't really see a world where using GenAI for both coding and QA gets us to where we want to go, unless as some people say, we start using formal verification (or other very rigorous and hopefully automatable advanced verification), at which point we'll have invented a new category of programmers (and we will need to train all of them since the vast majority of current developers don't know about or use formal verification).
AI can make you a basic signal for whatever group you want with zero oversight now anyway. The days of trying to proxy anti-encryption laws so you can spy on your people are numbered.
"This post is to underline that Nothing is inevitable."
Inevitable and being a holdout are conceptually different and you can't expect society as a whole to care or respect your personal space with regards to it.
They listed smartphones as a requirement an example. That is great, have fun with your flip phone, but that isn't for most people.
Just because you don't find something desirable doesn't mean you deserve extra attention or a special space. It also doesn't you can call people catering to the wants of the masses as "grifters".
