Nikhil Daga

@Im_IrushiK I will give you some advice instead. Stop writing fake stories.

Saw a guy coding today Tab 1 ChatGPT Tab 2 Gemini Tab 3 Claude Tab 4 Grok He asked every AI the same question. Patiently waited nd pasted each response into 5 different Python files Run all 5 files Pick the best one Like a psychopath What’s 1 piece of advice you'd give him?

@burkeholland It will never make any sense to write code by hand now. Don't restrict yourself to a number. You are more than that.

What is the max you would pay for AI per month before it would make more sense to write code by hand? I have a number...

@littledimple01 @sama @benhylak You are missing the most important step. People didnt hop from Anthropic and Google. They literally made people leave.

@sama @benhylak A is good B releases new version , B becomes good. C released new version, C becomes good. A releases a new version, A becomes good. How many times are people going to hop ?

codex is just night and day better than claude at ui design. claude, especially 4.7, is so bad it's hard to overstate.

@sama @benhylak Waiting

@benhylak this is rage bait right? but it will be the best soon!

@thsottiaux attached images appear cropped in codex and there is no way to see them fully

What are we obviously not getting right with Codex?

@thsottiaux Frontend.

@Bandz_Trading @corbin_braun It's a backend developer

@corbin_braun I don’t get how it’s so smart and so good at images and so bad at front end it actually doesn’t make sense

GPT-5.5 is amazing. but please don't use it for the frontend.

@mark_k @OpenAI Thinking mode is not thinking enough. It's answering without thinking. It has become fast but dumb

With @OpenAI ChatGPT, I really don’t recommend using “Instant” mode anymore. With GPT-5.5, Thinking mode has become so fast that it’s basically always worth using. At this point, the only real reason to keep Instant mode around is probably for Free tier users, simply to save GPU resources.

Anyone else getting? Reconnecting... 2/5 stream disconnected before completion: websocket closed by server before response.completed Reconnecting... 3/5 Reconnecting... 4/5 Reconnecting... 5/5

Pro Tip : Do not use Codex for frontend

@TheRohanVarma In real app usage, the 5 hour limit on $100 Pro Plan gets used within 2 hours

Today I’m attempting to hit the 5-hour limit on the Codex $100 Pro plan. The method: build a MapleStory-like game from scratch. 30 minutes in, I already have a working game with sprites, maps, and assets generated with Imagegen. Unfortunately, I’ve only used 5% of the limit so far. At this pace, I may need to start building RuneScape in parallel just to make a dent 😬

@cheatyyyy thats not true anymore. it stops within minutes of limit hit

is it wrong of me to kick off an extremely dense codereview when my 5 hour limit is under 10%? because codex won't stop until my task is complete surely this doesn't count as abuse.. right?

@thsottiaux • Unrecognized command '/goal'. Type "/" for a list of supported commands. What am I doing wrong?

/goal might be the most consequential thing we have shipped in codex The value of good instructions has never been higher.

@ProofofMaro Software Development & Astrology

What have you put 10,000 hours in?

@OfficialLoganK How?

AI is going to radically reduce the cost to run a marketplace

Who else is waiting for codex limit reset by @thsottiaux ?

@_christinacodes Coding is like swimming. Once you learn it, you dont forget it.

Have you all also forgotten how to code, or is it just me?

Hi @OfficialLoganK What do you think about the upcoming Gemini version compared to GPT 5.5?

People who have early access to the upcoming Gemini Pro model, is it better than GPT 5.5?