@DevAdventur3s do they get used in the order of expiration? So, soonest expiration gets used first?
I was laying in bed last night thinking about this.
English
Peter Copu
899 posts
Found a hidden-ish Codex usage detail today 👀
The app shows “2 resets available,” but the small menu does not show expiry dates.
I checked the Codex backend endpoint and made a tiny local helper that shows:
✅ available resets
⏳ grant date
📅 expiry date
Helpful if you want to use resets before they disappear.
#Codex #OpenAI
English
@jonathan_wilke when all interaction is replaced by text, why not the terminal?
English
I don't get the hype around CLI coding tools like Claude Code.
Human-computer interaction evolved past the terminal 30 years ago for a reason. UIs won.
Why are we regressing?
English
@catalinmpit install the telegram bridge on Mac/linux/windows: github.com/pcopu/coco
Just point your agent to it and it will guide you through installation.
English
@catalinmpit CLI uses less ram so I use it almost exclusively along with a telegram bridge to control it from my phone.
English
@catalinmpit throw some crumbs to us peasants. My tiny macbook air struggles...
English
Pitch me your startup in 1 sentence
The best ones I’ll genuinely take a look at and dm you feedback
English
@orcdev I use my own software every day. Reliable, malleable Telegram bridge to all my codex projects: github.com/pcopu/coco
English
@one_miloo Grain that goes up and down in relation to the width (quartersawn) is the most stable.
English
This is how you select the right lumber for your next project.
English
it’s wild that neither claude code nor codex allows me to just talk on my phone and send instructions to my coding agents on my computer
English
Hey @thsottiaux , this task has nothing to do with `gpt-image-2`. I'm just removing a parameter from a class. It keeps failing with this message and then stops in its tracks completely. Over and over.
English
@convex Unsure what this adds, convex + 5.5 is already flawless. Love your product, it makes software so much easier.
English
@willeastcott have you come across anyone working on Matterport to Splat workflows?
English
@anulagarwal @tibo_maker Maybe a crop video to portrait aspect ratio tool?
Ideally something that runs in browser and doesn’t touch your server?
English
OpenClaw starts out very fun, then the headaches start happening after a few weeks.
I’ve talked to many AI agent power users who are also struggling with OpenClaw.
Gateway issues, cronjobs not firing, skills not being used consistently, memory fall off, integrations need re-authentication, oscillating between overeager and undereager, not placing files in the right place. Etc
Matt Wolfe@mreflow
I don't know if this is a skill issue or something... But I've been playing with OpenClaw a ton for the past 4ish months. I feel like lately I'm spending more time troubleshooting issues with it and telling it what it's doing wrong than I am actually getting valuable use from it.
English
What’s the difference between
GPT 5.5 low reasoning + /goal
Vs
GPT 5.5 xhigh reasoning + one shot
Both are essentially yeeting compute at a task.
But which one
- is more efficient?
- works better & produces better results?
- finishes the task?
Seems like the major difference is low would spend less time thinking between each step? And would do way more tool calls because of this?
English
@AdamHoltererer Use this for audit and review: github.com/steipete/oracle
English
I paid for ChatGPT Pro, but I don't know what I'm supposed to be using GPT 5.5 Pro for.
Please, people who use it, tell me what I should be using it for, because I'm just giving everything to Codex.
English
@Statikoo Putting a torch that close to epoxy when you first pour is a big no-no.
It’s definitely ai.
English
I have 40 projects in my environment folder, mostly unfinished.
Focus is underrated.
English
We're watching Blackberry vs. Apple in real time.
Prepare for another OpenAI drop today/tomorrow.
Claude@claudeai
Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude. Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on the Pro, Max, Team, and Enterprise plans, rolling out throughout the day.
English