fb

coding the vibes

[fb @fbal98]

@tanishqk Looks something interesting to me, how can i try it?

[fb @fbal98]

@StuartDAA @tlbtlbtlb This is funny I will borrow it🤣🤣🤣🤣🤣

[fb @fbal98]

@testingcatalog

[fb @fbal98]

@_sy1vi3 @ProgrammerDude TIL 😮

[fb @fbal98]

@iuditg Definitely something wrong with your codex setup. Disable auto review. Disable memory. Ask one of your agents to audit the weekly windows of both codex and claude and see why the difference.

[fb @fbal98]

@avrldotdev ??

[fb @fbal98]

@thsottiaux Astra

[fb @fbal98]

@VictorTaelin you are right and %100 agree with you. people are sensitive these days

[Tibo @thsottiaux]

We unfortunately have decided that we cannot continue providing access to our models through Cursor and are ending our partnership. It boils down to trust and we’ve asked that this takes effect on November 12 to give you some time to plan.

Many have used the GPT models through Cursor and here are options we know should work in the future:

- We will continue to allow using your own OpenAI API key and similarly will continue to provide access through our IDE extensions for Cursor.
- We will keep working with the broadest range of tools and harnesses, some of which are OSS, but also many many closed-source ones.

We are as committed as ever to continue supporting developers and the flourishing ecosystem of tools, harnesses and products. We will also continue to invest in our own open-source initiatives and believe in broad optionality for developers.

You can read more about our decision in the blog:
https://t.co/Oj76Bkc2KX

[fb @fbal98]

@FanOfArteta @M1L4GR03 Lol I agree with you but I don't know how to explain that this is some kind of humor/satire not that it was meant literally.

[fb @fbal98]

@FanOfArteta @M1L4GR03 Actually that phrase is a prayer, and translation seems off. What the OP meant was rhetorical exaggeration.

[fb @fbal98]

@TokenGremlin Apparently,,

You are just dumb

[fb @fbal98]

@shownotover tf is wrong with these people. I have $200 sub and don't talk about nor touch ultra. what makes you think you can afford it for $20?

[fb @fbal98]

@ishuagra02 AFAIK its the same in claude

[fb @fbal98]

@migtito @hezarrfen @Zai_org Lmaoo

[fb @fbal98]

Yea I agree with you maybe grep is not the best, I am mostly interested in what people think is better so I can go ahead and prototype something and experiment if it is any good, you know?

IMO just give it sometime, next one or two generations of models will solve thiw issue. I strongly believe the fix is within the model/harness architecture not that some tool is slow, not semantic enough, etc..

[fb @fbal98]

Totally not true, this take is so bad and wrong.
Semantic search never made sense for codebases. Never.

Agent, like human, is better off performing keyword search (semantically) to find all references it needs. No need for extra complex bs to do the things we used to do as humans before.

On # 3, kinda okay take but it applies to semantic search as well, so actual solution is not better grep-ing but better ways to allow agents to cleanup their context without nuking cache, perfromance, etc....

[fb @fbal98]

@Achu_Ashwath_ @dillon_mulroy Why and whats trh alternatives?

[fb @fbal98]

@kentcdodds @theo Its definitely not a black and white here. Sometimes 5 agents are running but you are wtill waiting for that one agent doing devops stuff

[fb @fbal98]

@NovaXCode Lol but its right. I prefer models to say no than yes yes yessir when i do stupid things