Ali Alshehri

2nd-year CIS student @ccis_imamu
Ai enthusiast
having fun vibecoding

[Ali Alshehri @AliLoveAI]

@TheKidBuilds Yeah just tried it and plugged into cursor good experience thanks🤗

[Ali Alshehri @AliLoveAI]

That is actually not good news I have cursor pro+, devin pro and other subs

The only thing kept me using chatgpt was the generous weekly limit

I’m not a casual I just liked the workflow thru codex just because I don’t pay 100$ doesn’t mean my usage won’t matter

[Tibo @thsottiaux]

Tomorrow we will bring back the 5h limit for Plus accounts across ChatGPT Work and Codex. I had mentioned this a while ago, but then postponed it.

This is necessary as (a) the 5h limit allows us to smoothen the load on our compute, allowing to keep the plan generous in terms of weekly usage and (b) users on the Plus plan are relatively casual and new users, but then also just accidentally eat through their whole weeks usage and then are confused, making it not a great experience.

We are for the upcoming months keeping the 5h limit not enabled for Pro $100 and Pro $200 subscriptions.

[Ali Alshehri @AliLoveAI]

@TheKidBuilds @bot @billyjhowell @gregisenberg that is so cool also the Github issue manager seems like a thing i would need to baby sit pr's

[Ali Alshehri @AliLoveAI]

Best way for Big Phased planes is an agent on the look out with strict instructions
planner.md
implementer.md
and ofc agents.md

So Happy with this Workflow and devin is good

[Da7em @Da7_Tech]

For the past two months I've been building a new AI benchmark from scratch, based on real tasks from my own workflows across fields that current benchmarks barely touch.

The goal is a different read on model capability: strict evaluation, detailed explanations, and clear results on which model is actually best for which kind of work.

It stays 100% neutral and fair regardless of sponsorship.

I've already put over $12000 of my own money into testing the major models.

If any company wants to sponsor the project or provide credits, that means more models tested, more trials run, and a more rigorous final benchmark.

[Ali Alshehri @AliLoveAI]

I love kimi k3

@Da7_Tech ur vouch for it lowk saved my workflow

[Ali Alshehri @AliLoveAI]

@Da7_Tech Tried it on my non updated codex it ran greatly but people reporting its gone

[Ali Alshehri @AliLoveAI]

@Da7_Tech 😳😳 that’s big big wow good luck da7 I will be on my toes for this project

[Ali Alshehri @AliLoveAI]

@Da7_Tech Fable before it got lobotomized was S++
I still have the work it done on some of my projects enjoyed every bit

Hope we can go back to mythos sooner then later

[Ali Alshehri @AliLoveAI]

@jun_song Once regulated it will never feel the same

Data Retention will be forced prices of subs would sky rocket

[Ali Alshehri @AliLoveAI]

@TheKidBuilds I review strong models with themselves with higher effort and a review prompt

[Ali Alshehri @AliLoveAI]

My Advisor is flabbergasted

((The numbers confirm it was far beyond a reasonable foundation task: 86 files, 14,131 insertions, 6,182 deletions, including a new 1,968-line integration test and broad production-route churn. Even excluding lockfiles and whitespace, it was roughly 6,700 additions across 84 files))

[Ali Alshehri @AliLoveAI]

gpt 5.6 sol did all that
10 subagents
4 hours of work for simple diff im so confused
my usage is gone lmao

[Ali Alshehri @AliLoveAI]

@Da7_Tech Actually the most fair list i saw

[Ali Alshehri @AliLoveAI]

@Sh_0o5 كلامك ماهو عادل كل مودل يفرق عن الثاني بشكل كبير مره

يمدي اخش كودكس واختار 5.5 ويخبص لي مشروعي😅

[Ali Alshehri @AliLoveAI]

@Da7_Tech Brilliant da7em what about token minimization do you work with something strict ?

[Ali Alshehri @AliLoveAI]

Thank you so much @poteto @cursor_ai

Love cursor
10/10 customer appreciation

[Ali Alshehri @AliLoveAI]

@fawnunwrap @bil0090 I still have it did you update codex ?