🚨 codex users!! PLEASE DO NOT BUY CODEX!! I have $20 codex I used GPT-6 Astra of Max I asked it: "Here is the project, create a promo video. Give me your best" and disabled all the skills Now... the results are... BAD: - 2.4 Million tokens ONLY!!!! -... 14% weekly limit used (98% of 5 hr limit) - 29 minutes of work - $5.7 API usage!!! This is absurd!! Only ~$40 of usage weekly?? Claude gave me 40 Million tokens for 13% weekly!!! And the output?? Unnecessary object and off-grid placements of bars... I can't use it Needs a LOT of work ngl I'd highly recommend switching to claude right now (for this month) NOTE: I used "max" because this is completely logical stuff... so it had to think to its max capabilitiesshow more

I’ve found the same thing! Why use codex anymore when they’re cutting usage and releasing terrible models over and over? They’re really struggling

same bro... Don't use it now... they were good 2 months ago

For Codex users from an EX Codex user... 75% in 11 minutes 👌🤦‍♂️🤦‍♂️🤦‍♂️

That's sad 😭 Codex used to be so good

Codex is still the best 20 dollar plan. not for value, but because Claude doesn't have anything that matches ma boi luna. 5x and 20x? go to claude. 20 dollar plan? Codex. For Luna.

Yeah bro 💯 If you need unlimited coding, go with Codex because of Luna... I can't argue here... no sub does that

@shownotover careful with token limits! I hit a wall when I tried maxing out features. Sometimes less really is more.

You are right but the problem is, right now, the task was entirely logical and had nothing to read about so it was a good decision to use it on Max. Otherwise it wouldn't make sense. 🥲

You might get better results at a lower reasoning level. Asking it to do max reasoning for such a simple prompt is likely making the model over-reasoning. This is very far from the "PHD level research" that max reasoning is designed for.

Okay sir... Will do a test for medium... Let's see the results

Interesting, looking forward to seeing the results.

on Pro 200$ you have approximately: 1b tokens on Astra 6b tokens on Sol (I have calculated before astra release) 14b Terra ~120b-140b Luna (not exact because it's between Astra and Sol 😅) Calculations based on usage

If I assume that's weekly... Then you get around 400 Million tokens for Opus 5.5 (better than Astra) for only 1/10th of the price... I don't think Codex is worth it now 🥲

yes, I have counted weekly limits :)

I kinda solved this problem, just wrote a huge post about it

Tag me in bro.

Here you go, bro. I did a lot of research and built this harness to get more out of my subscription:

Your mistake is using max. Don't get me wrong, Astra blows through limits, but you do not need max effort for just about anything.

Bro, this was a logical task. That's why I used max effort. I did the same with Opus 5.5 on max (same prompt) and it didn't blow up with the usage limit like the one Astra did.

Opus 5.5 also shouldn't be used on max. See Theo's Opus 5.5 video for the reasons why, they're valid. It's not even about usage. Max effort forces the models to think more, which not only leads to more token usage, but it also can lead to worse outcomes because they think themselves in circles.

Claude code 👑

Using Opus 5.5 as my main orchastrator

I want to switch, But can't since I'm banned from Anthropic for being Under 18

Try @cognition ... Good usage for all models

yeah the quality isn't as good as opus 5.5 but comparing api costs and tokens counts is not right way to compare codex vs claude

So... what should be the way? We are paying $20 for both... One gets better quality, more work done tbh... ain't that good?

yeah bro i agree but API costs and token counts isn't right way here 😅 codex is heavily efficient (uses way less tokens and costs way less too compared to claude) so you can't compare lemons to apples you getting it right ?

Okay I understand the basics: one is token-efficient and the other one uses a lot of tokens. At the end of the day we all care about quality and the amount of work done. Seeing Codex and Claude code in action, I can say to you and write it for you on paper that Claude does two times the work Codex does for the same amount of money.

okay bro 😅 so compare it like that make 2 branches and see which one is doing how much work and not just try to burn limits and yeah i know currently Opus 5.5 is doing more work (coz its cheaper a bit now)

that's really good no? on my sub Astra on low lasts like 5 minutes and dies right after

try Claude... and if not, try Cursor

Quality wins. $5.7 barely dents the $20, so the 29 minutes are the real bill.

bro 😭 Why you using AI

Yeah I have tried with Astra and man it was horrible

$20 on Astra is horribly horrible haha still, I only had $20 so... what could have I done 🤣

@thsottiaux @victornunez @OpenAI @sama

@thsottiaux @victornunez @OpenAI @sama Nope... they are gonna say "DevDay"

2.4M tokens burned for a promo that still looks mid. that weekly % hit different

Yeah bro... But tell me one thing Am I not good enough for a human being that you have to use AI to respond? If I wanted to talk to AI ... Why would I make this post?

Burning 2.4M tokens on a bad video hurts. We'd rather burn them on our own apps.

XFastest is my own app 🥲

didn't realize XFastest was yours. that 2.4M token run hits different when it's yours

A.I is do good now

Its gonna come after us in 10 years haha

dude

What is it sir? 😀

why are u so cringy bro....

what do you mean?

Now we are monthmaxxing depending on the model 😄

Well, gotta save $ where we can 🙂

Kkkkkkkkkkk você tá de sacanagem com a minha cara certo? É uma piada??? Com o plano plus apenas vc usa o astra no Max, envia um promot literalmente dizendo "crie um vídeo, faça seu melhor" recebe um resultado ruim e vem bostejando aqui? Primeiro aprenda usar ferramentas de ia

This is what Claude did with exactly the same prompt. That is why I tested Astra like this.

Use Astra to create then Opus fix the "taste"

That'll simply mean I am using Astra as implementor and Opus as Orchastrator

Good stats, Claude indeed seems way better!!!

yeah bro! I had switched to claude

Opus 5.5 is 50x better than this for the same use case. I don’t know how OpenAI randomly dropped the bag

I even created a video on Opus 5.5 and it was so much better. OpenAI used to be a lot better.

It’ll flip again when the new models come out I’m sure. It’s just one beating the other in a loop.

Ok, I’m usually not the guy to comment on this, but this pissed me off a little. Most of the time a model is as good as the prompt you give it. Of course sometimes a model comes around that does better with less, however, more often then not the more specific you explain what you want the better the result will be. I did the same with GPT-6 Sol on High effort.

Same prompt and same $20 sub btw Now choice is yours if you get pissed or open your eyes

perahps high or extra high could've been more than enough; htese models are pretty good and avoid it having it "overthink" itslef in a loop at times

Hmm... When I use Opus 5.5 on max, that doesn't hurt... but when I use Astra on Max, that starts hurting?? why is that? I want maximum capability by the Model that I can get out for one task that I want to be the best. am I missing something?

these really work well

🥲 I guess if it works for you, I support you bro

Your posting style 🤣 not codex

😁 From Social media, I have learnt that the more you have emotions in your content, the more people will relate to it. ofc yapping doesn't count so have to do it like this ☺

Yeah thats why I shout all the time 🤣. The more emotions you can stir the better

"First time?"

Tremendo lameculo de Darío y famboy de anthropic

you had some serious brainwash to not see the clear difference between the quality to cost ratio can't argue with you

A ver todo sabe que anthropic le importa sus cliente empresarial y nos a su usuario normales y lo que hace con 5.5 opus es para su IPO y cuando ya eso pase será la misma mierda que antes y openAI tiene modelo más potente intenamete ok

So let’s see if Tuesday addresses this, I like the idea that the 6th dot is for multi agent mode, and ties into the M&Ms they’re going for

no one cares

This is really unacceptable. Codex's quota is too tight compared to Claude, I'd better not buy it for now.