almost 12 hours deep into a single /goal loop and codex is still meticulously reviewing its own diffs. 472M tokens later and we have a clean build.
English
BrightyBrainiac
771 posts
BrightyBrainiac
@clasher11102
Not optimizing for being the best. Optimizing for being the most distinct. First principles, deep math, real systems — the long way, on purpose.
Katılım Eylül 2022
221 Takip Edilen14 Takipçiler
@nuno_schumacher @hiarun02 Right!!! I feel like this is the 3rd time I’m seeing this posted from the same account.
English
@clasher11102 @hiarun02 this platform is 70% engagement farming, it’s awful
English
Why keep paying for Claude Code or Codex when a free alternative just dropped?
A new coding agent is out, completely free, with support for multiple models like:
> DeepSeek v4 Pro / Flash
> Kimi K2.6
> MiniMax M2.7
Quick setup:
"npm i -g freebuff"
It can write code, execute commands, and help build full projects end-to-end.
Only tradeoff? A few ads here and there, similar to what you’d see in the demo.
English
English
Don’t you wish OpenAI released that 2000$ subscription now.
First Squawk@FirstSquawk
AI MAY NOW BE MORE EXPENSIVE THAN HUMAN EMPLOYEES, ACCORDING TO AXIOS.
English
Recruits, your first prize is here...
A custom GeForce RTX 5080 Founders Edition + PC copy of the game.
Comment #007FirstLightRTX to win 👇
English
@RaeAlisa_ @lucent_ai Codex because, obviously, the limits - duh.
But I also want to try 5.5 Pro.
English
to celebrate 3 months since lauching @lucent_ai, we're giving away 5 Codex Pro / Claude Max plans 🎁
to enter, like this post + comment which one you'd pick (codex vs claude)
winners will be selected from comments in 5 days 🫶
English
@hiarun02 You sure? I think the usage limits have just been glitching hard lately, maybe they are testing it.
English
@clasher11102 Yep. Bigger context helps, but avoiding compact thrash mid-task is the real win.
English
BrightyBrainiac retweetledi
figured out the broke $20 Plus workflow.
If you really want to squeeze every inch of your $( let’s be real here, this is basically exploitation) -> it’s 5.4 xhigh + the 1M context window.
Because you won’t hit the “auto-compact fail” error you would on 5.5 with 256K.(/goal)
English
@thegenioo Looks cooler, feels cooler.
I also find it more seamless for whatever reason.
English
@cerebras @cognition So they’re saying SWE-1.6 beats Claude on speed. Bold claim to make on a platform where half the audience uses Claude.
I’d like to find out.
English
🎁 We're giving away 5 Windsurf plans ($250 credit each)!
Try SWE-1.6 — @Cognition’s latest fast and intelligent agentic coding model, powered by Cerebras. In a side-by-side with Claude, the speed difference is clear. More iterations, faster fixes, better code.
💬Comment why you want access to enter. Five winners will be selected at random within 48 hours.
English
I’m giving away all the merch I got from the GPT 5.5 event.
This weekend I’ll be whipping up a little app in Codex of course, to pick three winners.
If you want to add your name to the list, comment below. Cutoff time will be 9am PST on Saturday.
Morgan@morganlinton
I’m going to give away every piece of swag I got at the OpenAI event tonight. Of course very appreciative to get it 🙏 But, never been a swag guy, and know so many people love this stuff, so would like to see it go to a good home. Will share more tomorrow or Thursday, but if you want some swag from the event, comment below and I’ll add you to the random drawing. And I’ll ship it to you for free. Let’s let the GPT 5.5 love go around 🫶
English
Final update: it is still going. over 30 min now.
wonder if this is a known thing @thsottiaux because I am a TUI user, and have never experienced it there.
BrightyBrainiac@clasher11102
Found something new. If its pursuing a /goal and you have hit the usage limit, and you have hit the context window limit as well, Its just gonna keep running into this loop of trying to compact, but failing because of usage limit.
English
Yep, still going, over 5 minutes now.
I wonder if its just gonna keep going till the limit resets?!
BrightyBrainiac@clasher11102
Found something new. If its pursuing a /goal and you have hit the usage limit, and you have hit the context window limit as well, Its just gonna keep running into this loop of trying to compact, but failing because of usage limit.
English
Found something new. If its pursuing a /goal and you have hit the usage limit, and you have hit the context window limit as well,
Its just gonna keep running into this loop of trying to compact, but failing because of usage limit.
English
While I slept, Codex was building an operating system.
Still going, just crossed the 9 hour mark.
I think @steipete had a record of something like 29 hours for /goal, attempting to beat this 😅
Morgan@morganlinton
/goals is still running - Codex is actually building an operating system, from scratch, given inspiration from Steve Jobs when he built NEXT, but accelerated into the current timeline. I think it's going to run all night, could keep going all day tomorrow. Totally wild.
English