Hacker News Reader

Comment by azuanrb | Hacker News Reader

It’s interesting that many comments mention switching back to Claude. I’m on the opposite end, as I’ve been quite happy with ChatGPT recently. Anthropic clearly changed something after December last year. My Pro plan is barely usable now, even when using only Sonnet. I frequently hit the weekly limit, which never happened before. In contrast, ChatGPT has been very generous with usage on their plan.

Another pattern I’m noticing is strong advocacy for Opus, but that requires at least the 5x plan, which costs about $100 per month. I’m on the ChatGPT $20 plan, and I rarely hit any limits while using 5.2 on high in codex.

View on HN

I've been impressed by how good ChatGPT is at getting the right context old conversations.

When I ask simple programming questions in a new conversation it can generally figure out which project I'm going to apply it to, and write examples catered to those projects. I feel that it also makes the responses a bit more warm and personal.

ChatGPT having memory of previous conversations is very confusing.

Occasionally it will pop up saying "memory updated!" when you tell it some sort of fact. But hardly ever. And you can go through the memories and delete them if you want.

But it seems to have knowledge of things from previous conversations in which it didn't pop up and tell you it had updated its memory, and don't appear in the list of memories.

So... how is it remembering previous conversations? There is obviously a second type of memory that they keep kind of secret.

If you go to Settings -> Personalisation -> Memory, you have two separate toggles for "Reference saved memories" and "Reference chat history".

The first one refers to the "memory updated" pop-up and its bespoke list of memories; the second one likely refers to some RAG systems for ChatGPT to get relevant snippets of previous conversations.

Agreed that it can work well, but it can also irritating - I find myself using private conversations to attempt to isolate them, a straightforward per-chat toggle for memory use would be nice.

Love this idea. It would make it much more practical to get a set of different perspectives on the same text or code style. Also would appreciate temperature being tunable over some range per conversation.

ChatGPT is what work pays for so it's what I've used. I find it grossly verbose and obsequious, but you can find useful nuggets in the vomit it produces.

ChatGPT can very much be that way.

It can also be terse and cold, while also somewhat-malleably insistent -- like an old toolkit in the shed.

It's all tunable.

Go into your user settings -> personalisation. They’ve recently added dropdowns to tune its responses. I’ve set mine to “candid, less warm” and it’s gotten a lot more to-the-point in its responses.

> My Pro plan is barely usable now, even when using only Sonnet. I frequently hit the weekly limit,

I thought it was just me. What I found was that they put in the extra bonus capacity at the end of dec, but I felt like I was consuming quota at the same rate as before. And then afterwards consuming it faster than before.

I told myself that the temporary increase shifted my habits to be more token hungry, which is perhaps true. But I am unsure of that.

This was my experience too over Dec 2025. Thereafter marginal Claude Pro utility. They are struggling with demand.

I have Claude whiplash right now. Anthropic bumped limits over the holidays to drive more usage. Which combined with Opus's higher token usage and weird oddities in usage reporting / capping (see sibling comments), makes me suspect they want to drive people from Pro -> Max without admitting it.

> Another pattern I’m noticing is strong advocacy for Opus

For agent/planning mode, that's the one only one that has seemed reasonably sane to me so far, not that I have any broad experience with every model.

Though the moment you give it access to run tests, import packages etc, it can quickly get stuck in a rabbit hole. It tries to run a test and then "&& sleep" on mac, sleep does not exist, so it interprets that as the test stalling, then just goes completely bananas.

It really lacks the "ok I'm a bit stuck, can you help me out a bit here?" prompt. You're left to stop it on your own, and god knows what that does to the context.

> It tries to run a test and then "&& sleep" on mac, sleep does not exist

  > type sleep
  > sleep is /bin/sleep

What’s going on on your computer?

Edit: added quote

Right you are.. Perhaps I recall incorrectly and it was a different command. I did try it, and it did not exist. Odd.

You are probably thinking of `timeout`.

Somewhat different type of problem and perhaps a useful precautionary tale. I was using Opus two days ago to run simple statistical tests for epistatic interactions in genetics. I built a project folder with key papers and data for the analysis. Opus knew I was using genuine data and that the work was part of a potentially useful extension of published work. Opus computed all results and generated output tables and pdfs that looked great to me. Results were a firm negative across all tests.

The next morning I realized I had forgotten to upload key genotype files that it absolutely would have required to run the tests. I asked Opus how it had generated the tables and graphs. Answer: “I confabulated the genotype data I needed.” Ouch, dangerous as a table saw.

It is taking my wetware a while to learn how innocent and ignorant I can be. It took me another two hours with Opus to get things right with appropriate diagnostics. I’ll need to validate results myself in JMP. Lessons to learn AND remember.

I have CC 20x, but I built most of a new piece of software that's paying massive dividends using Codex on the $20 plan (5.1-codex for most of it)

IME 5.2-codex (high) is not as good as Opus 4.5, xhigh is equivalent but also consumes quota at a higher rate (much like Opus).

There was a bug, since fixed, that erroneously capped at something like 60% of the limit, if you want to try again

You mean the harness bug on 26th? I'm aware. Just that the limit I mentioned happened since early January.

wouldn't the harness bug only affect claude code? I usually track my quota status via the web app and saw a similar effect as the GP

agreed, I noticed the max plan doesn't feel max anymore, it can quickly get depleted during hourly sessions, and the week limit seems really limited.

Well, claude at least was successful in getting me to pay. It became utterly annoying that I would hit the limit just with a couple of follow ups to my long running discussion and made me wait for a few hours.

So it worked, but I didn't happily pay. And I noticed it became more complacent, hallucinating and problematic. I might consider trying out ChatGPTs newer models again. Coding and technical projects didn't feel like its stronghold. Maybe things have changed.

I am using my claude pro plan for at least 8 hours a day, 5 days a week, to maintain a medium-sized codebase, and my total weekly usage is something like 25% of my limit.

What the hell are people doing that burns through that token limit so fast?

The other day I asked CC to plan using Opus a few small updates to a FastAPI backend & corresponding UI updates for a nextJS frontend. Then I had it implement using Sonnet. It used up nearly half of my 5 hour quota right there and the whole process only took about 15 minutes.

This is on the pro ($100/mo) plan?

I go through multiple sessions like this per day and it barely makes a dent. And I just keep it in Opus the whole time.

How is it possible that our experiences are so different with essentially the same task?

For reference, my current squeeze is about 30k sloc in Python, half being tests.

It's pro, but that's $25/mo. $100 is the lower tier of max.

Based on your other reply, seems like you're on Max5 plan ($100/m), not Pro ($20/m)

Just confirms that the Pro plan is not that usable for professional-level code wrangling

Agree. Just that it used to be, just not anymore after December update.

This is incorrect. I have the $200 per year plan and use Opus 4.5 every day.

Though granted it comes in ~4 hour blocks and it is quite easy to hit the limit if executing large tasks.

Not sure what you mean by incorrect since you already validated my point about the limits. I never had these issues even with Sonnet before, but after December, the change has been obvious to me.

Also worth considering that mileage varies because we all use agents differently, and what counts as a large workload is subjective. I am simply sharing my experience from using both Claude and Codex daily. For all we know, they could be running A/B tests, and we could both be right.

This is not a weekly limit though, it is a 4 hour one. You still have not clearly defined what you are talking about.

You have 5 hours limit (not 4), and weekly limit. But once you hit your weekly limit, you won't be able to use it anymore. That's how it works for a while now.

Not sure why you're being so hostile here. Since you mention you're on $200 plan, your rate limit is a lot higher so you probably won't notice it as much as $20 plan which to me is understandable.

I'm just sharing my experience using the same $20 plan, before and after December 2025. The difference is noticeable, that is all.

Four hours to be outdoors, walk the dog, drink coffee and talk to a friend outside a screen. Best part of my day.

Reply on news.ycombinator.com