I feel like they are making it harder to use it this way. Encouraging autonomous is one thing, but it really feels more like they are handicapping engaged use. I suspect it reflects their own development practices and needs.

This is something I've thought of as well. The way the caps are implemented, it really disincentivizes engaged use. The 5-hour window especially is very awkward and disruptive. The net result is that I have to somewhat plan my day around when the 5-hour window will affect it. That by itself is a powerful disincentive from using Claude. It has also caused me to use different tools for things I previously would have used Claude for. For example, detailed plans I use codex now rather than Claude, because I hit the limit way too fast when doing documentation work. It certainly doesn't hurt that codex seems to be better at it, but I wouldn't even have a codex subscription if it wasn't for claude's usage limits

Wow, weird to see someone mirror my experience so closely. At the $100 plan my day was being warped around how to maximise multple 5 hour sessions so that it felt worth it. Dropped down to the $20 plan and stopped playing the game as I know I'll just consume the weekly usage in the few days I have free. Meanwhile codex gave me a free month, their 5HourUsageWindow:WeeklyUsageWindow ratio feels way better balanced and it gets may more work done from it. Similar to you, any task involving reading/reviewing docs [or code reviews] now insta-nukes claude's usage. My record is 12 minutes so far...

Another big one for me is that they dropped the cache TTLs. It is normal for me to come back to a session an hour later, but someone "autopilot"-ing won't have such gaps.

not just the cache though. every time you stop and come back, it basically reloads the whole session. if you just let it keep going, it counts like one smooth run. you hit the wall faster for actually checking its work.

It was probably the bug about cache getting purged after 5min rather than 1hour. You can review things pretty well within an hour. 5min is a real crunch. 5min doesn't mix with multitasking or getting interrupted.

My mental model for LLM is I don't expect them to chew gum and walk at the same time. Cleaning code up is a different task from building new functionality.

GLM always feels like it's doing things smarter, until you actually review the code. So you still need the build/prune cycle. That's my experience anyway.

It sounds like we have very similar usage/projects. codex had been essentially uncapped (via combination of different x-factors between Plus and Pro and promotions) until very recently when they copied Anthropic's notes.

Plus is still very usable for me though. I have not tried Claude Pro in quite a while and if people are complaining about usage limits I know it's going to be a bad time for me. I had to move up from Claude Pro when the weekly limits were introduced because it was too annoying to schedule my life around 5hr windows.

I started using codex around December when I started to worry I was becoming too dependent on Claude and need to encourage competition. codex wasn't particularly competitive with Claude until 5.4 but has grown on me.

The only thing I really care about is that whatever I'm using "just works" and doesn't hurt limits and Claude code has been flaky as all hell on multiple fronts ever since everyone discovered it during the Pentagon flap. So I tend to reach for ChatGPT and codex at the moment because it will "just work" and there's a good chance Claude will not.

It would be funny but not very flywheel so the one that gets there is more likely to get a gunner.

TBH the AI that "gets there" will be the biggest bullshitter the world has ever seen. It doesn't actually have to deliver, it only has to convince the programmers it could deliver with just a little bit more investment.

I seems like we need better standard libraries, but standard libraries turn into tarpits. I sort of like the way python's stdlib works.

It may have changed but there are (or used to be) gym memberships that would only let you cancel if you could prove that you moved and your new primary residence was more than one hour from the nearest branch. (I'm pretty sure there was a law passed to end this practice, but it was widespread)

It's an interesting form of tree shaking.

The overlap of bugs being found, nobody caring enough to bother read the reports or fix the code, and nobody caring that the modules are pushed out of main seems good.

I think the test is that new sign-ups won't have it and will the loss of five new Pro subscriptions be offset by more than one new Max subscribers.

Plenty of Pro subscribers never touch claude-code.

Although the ones that never touch claude code are a free $20 a month, the ones that do are potentially a seventy to eighty dollar twenty dollars a month . it’s not instantly obvious which customers you prefer (revenue vs cash negative growth- on second thought obviously they prefer the second)

They've preferred the second so far, but they might have a fair reason to see if they can keep growing with the first one instead or cut down on some loss leading, right?

How can you run the A/B test with mismatched documentation?

Yeah, theverge is subscription now.