aleqs

100%

If you don't want to have a discussion don't post pointless metrics that you don't even understand.

'experts' lmao. Your entire argument boils down to an appeal to authority fallacy.

The reason that US and its allies/friendlies always score high on these kinds of ratings while their enemies/adversaries always score low is because these institutions and 'experts' are directly funded by and beholden to these countries/interests.

Just look at Russia - it's score is highest in the 90s - the most corrupt and destitute time in its modern history, also happens to be when it was deemed somewhat friendly to US and friends.

Opposite of my experience - openai models, and codex are clearly the slowest (out of 5 different models/harnesses I use on a regular basis).

Nah, it's the best time (if you can). This is the time to spin up your own company/product and steal maximum marketshare from enshititech.

that just sounds like openai/anthropic cope/propaganda, based on absolutely nothing objective lol

even their harnesses are far surpassed by pi and opencode at this point

also sick 'rumors' lmao, apparently marketing through rumors is in vogue these days

GitHub is now one of the least reliable services in my stack, I'm in the process of moving everything off and keeping it for public/open projects for discoverability/discussion purposes only.

I've also noticed a meaningful decline in the quality and reliability of several other major software/apps and services - notably Google maps, Spotify, codex. (Is this because of AI?)

Codex, especially, is a strange one - initially I added it beside Claude code thinking it would actually be a higher quality, faster alternative (even if the model/harness is not quite as good at coding as Claude code/opus), and it seemed that way for the first few weeks. At this point though, codex is completely unusable for me - the contexts from different sessions are polluting/mixing with each other, prompt history is mixing/polluting each other. Codex randomly enters safe sandbox mode or whatever multiple times a day per session - it just starts seeing everything as read-only and loses tool and MCP access. It also randomly gets interrupted all the time for no apparent reason - 'your session has been interrupted' - so much for 'autonomous'. And holy shit codex is sooo slow, I'm guessing there are both server side and client side rate-limits, I have the 20x pro plan and I can't even use it up (I use up my Claude code pro 30x in 2-3 days, though to be fair Anthropic usage limits are arbitrary and low), because it is so slow plus all of the issues and constant random stops/blockers that prevent any kind of long-running autonomous work.

Opened a couple codex issues on GitHub for these things - all closed as duplicates. I look at the existing issues - all closed as resolved.

What a horrendous shitshow.

That just means your use is limited not that the plan is unlimited.

Nothing about it is unlimited or even close to it. Just because you only use 1gb of your 2gb data plan, doesn't mean you have unlimited data.

> Opus 5.5 right now because it's nearly unlimited use

Anthropic has some of the lowest usage per $ in general, not sure what you're taking about.

I would argue performance optimizations help with local/open models but hurt openai and anthropic - because open and or cheap/alternative models are threat to those companies. There is a fundamental contradiction/conflict between the prevelance of open models and the financial success of openai and anthropic. That is why they are doing everything they can to kill any open/cheap/efficient/chinese models (take a look at this thread - it was top of HN 40 mins ago, with very high engagement... now it is buried in page 5... totally normal and legit).

Yeah, you need a lot of resources in order to waste a lot of resources. Look at codex and Claude code - these trillion dollar companies 'with top talent' cannot build what open code and pi/oh-my-pi have built in the open for free? Both codex and Claude code, are slow, buggy pieces of shit (and I say that as someone who still heavily uses both for work, moved to open code and pi for personal stuff). The reality is these companies mostly focus on marketing and market capture through, non-competitive means - their services and software are unreliable, buggy trash.

Why did this thread suddenly massively down ranked? It was at the very top 15 mins ago, now it's on page 4 and dropping fast despite very high engagement... @dang

You're assuming product people don't 'invent' work, which is faaaar from true. The more technical the area, the more nonsense 'product' generates, that engineering then has to either redo, clean up or fight. The 'product' people on 'product-led' teams also generally own the internal comms and marketing (internal) side of things, which often has the effect of silencing engineering (and many other negative side effects). (Not always but often imo)

Engineers should understand their customers and their product (whether internal or external), should understand their metrics, and should be able to make intelligent, informed decisions. Sticking a non-technical 'product' (aka marketing) person into the mix is generally net-negative imo.

I think it has more to do with the fact that Stripe has already 'won' in a lot of ways, and the company has now basically transitioned from the innovative tech startup phase to the MBA/marketing/bureaucracy phase. Quality, efficiency as priorities are replaced with marketing and 'strategy'...

I really don't have a problem with you using AI, as long as you review and validate/test what it writes, and seems like you did that. Great project btw!

The author literally said:

> There might be some AI-isms in there, because agents just can’t help themselves to dump their arcanae in there.

The readme was very clearly AI-written (or at least heavily AI-assisted)... not saying that's a bad thing, and I agree it's fairly well written... but it is very obviously AI

As someone who has worked there as well, this is just funny to me.

Yes, this is on the right roadmap, and going to be prioritized now that someone has a real use case. Thanks!

I've been working on a general repository linter. The idea is to declaratively define a set of rules/conventions for your repo, (for things that language-specific linters don't cover), covering things from directory structure, required files, file staleness/freshness, file size, rules for binary files, rules around use of invisible Unicode, etc. - which can be checked deterministically. Many/most large repos have a set of hand-authored scripts for doing these kinds of checks, the tool I'm building basically packages these in a fast, reusable and extensible tool, with some niceties added.

https://alint.org/

https://alint.org/blog/why-alint/

Yeppp, I've been seeing this Jacob Coxon [0] guy popping up all over legacy media for the past couple days nonstop...he claims he quit OpenAI and Anthropic because the models are getting 'too smart' and that's dangerous, etc. The typical AI fears mongering drivel, without seemingly any criticism, at all, of the companies he quit supposedly because of these AI fears... and of course the mainstream media appearances prefix the interviews with this guy with 'this is not a marketing stunt'[1]... which, obviously, it is.

[0] https://www.cbsnews.com/news/anthropic-researcher-jacob-coxo...

[1] https://www.cnn.com/2026/09/09/tech/ai-anthropic-safety

Seems just like another case of collusion - continuing the story of VCs pushing all of their companies to use each other and 'stay within the network'. The good news (kinda) for the rest of us, is that many of these VC marketing/product/'strategy' people aren't actually all that competent - this is literally the best they can come up with.

I use alint [0][1] to define and enforce rules about files/globs that should or shouldn't be committed, among other things. You can configure it run as a pre-commit hook or in CI.

(disclaimer - this is my own tool)

[0] https://github.com/asamarts/alint

[1] https://alint.org/docs/rules/git-hygiene/git_no_denied_paths...

I use alint [0][1] to define and enforce rules about files/globs that should or shouldn't be committed, among other things. You can configure it run as a pre-commit hook or in CI.

(disclaimer - this is my own tool)

[0] https://github.com/asamarts/alint

[1] https://alint.org/docs/rules/git-hygiene/git_no_denied_paths...

You can also use something like alint [0][1] to define and enforce rules about files/globs that should or shouldn't be committed, among other things. You can configure it to run as a pre-commit hook or in CI.

(disclaimer - this is my own tool)

[0] https://github.com/asamarts/alint [1] https://alint.org/docs/rules/git-hygiene/git_no_denied_paths...

I use alint [0][1] to define and enforce rules about files/globs that should or shouldn't be committed, among other things. You can configure it run as a pre-commit hook or in CI.

(disclaimer - this is my own tool)

[0] https://github.com/asamarts/alint

[1] https://alint.org/docs/rules/git-hygiene/git_no_denied_paths...

I see no banner, but I use an ad blocker configured to reject and hide all such banners, like a sane person.

Direct codex and Claude are both down for me. Both work via AWS bedrock.