Hacker Newsnew | past | comments | ask | show | jobs | submit | naiv's commentslogin

Feels slower than GPT-5 and I understood it that medium should be a lot faster than high but for me it's almost the same , so I don't see a reason preferring medium.

The pelican is not so convincing though :)

So a bit in line with what Theo mentioned in his video that he was not happy with the ui capabilities


Good point I forgot about the pelican!

https://help.openai.com/en/articles/11369540-using-codex-wit...

have to say not sure what this even means and what the exact definition of a message is in this context.

with claude code max20 I was constantly hitting limits, with codex not once yet


Same. We're not hitting limits at all with Codex and it's ridiculously good at managing and preserving its context window while getting a metric fuckton of work done. It's kind of unbelievable actually. I don't know re billing. Not my dept.

The model providers should analyse the tone of the instructions.

Before I finally gave up on Claude Code, I noticed that I got more aggressive towards it, the more stupid it got as I could not believe how dumb it started to be.

And I am sure I was not the only one.


I think this is directly related to https://x.com/sama/status/1965110064215458055

And I think it was 100% on purpose that they degraded the model performance as Claude Code got so popular and they either ran out of capacity or were losing money too fast.

But now that people are fleeing to Codex as it improved so much during the time, they had to act now.


They will probably also release sonnet 4.2 or something soon to make people jump back again to try it and hopefully restick

If Codex CLI was even half as good as Claude Code's CLI, I'd seriously consider moving.

But alas it's not. It looks like some intern whipped it together.


I wonder how long the myth of AI firms losing money on inference will persist. Feels like the majority of the evidence points to good margins on that side

> I wonder how long the myth of AI firms losing money on inference will persist. Feels like the majority of the evidence points to good margins on that side

If they're not losing money on inference, then why do they need to keep raising absurd amounts of money? Like, if inference is profitable and they're still losing lots and lots of money, then training must be absurdly expensive, which means that basically they invest in quickly depreciating capital assets (the models) so not a good business.

I think Anthropic is an interesting case study here, as most of their volume is API and they don't have a very generous free tier (unlike OpenAI).


> If they're not losing money on inference, then why do they need to keep raising absurd amounts of money?

I recently heard someone say that ~"state of the art LLMs are the most rapidly depreciating asset in history."

This seemed accurate sounding to me. Anyone else have thoughts on this?


same with google lens, I do understand the motivation / laws behind it but yes , it really is a let down.

Same thing with models and cosplayers. Even Yandex isn't quite the same anymore I think.

Can be sometimes circumvented with cropping / stronger compression, but it made looking up who a given image is of / what imageset is it from pretty annoying - the opposite of what these people would want in this case too.

Sometimes I wonder if celebrities have issues using tech because of these checks.


Same. We all moved to codex in the past weeks not looking back at our cancelled Max20 subscriptions.

But who knows what will be to best tool/model to use in October.


The past 3 releases of Codex have massively improved the user experience and output quality. I prefer it over Claude Code now and cancelled my Anthropic Max20 subscription in favor of Gpt Pro.


You can sign up for a subscription and pay from $20-$200 flat with some daily/weekly restrictions on token usage.

https://support.anthropic.com/en/articles/11145838-using-cla...


at the end he says "not just claude code. any agents"


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: