Felipe Coury 🦀 (@fcoury) header
Felipe Coury 🦀 (@fcoury) profile picture

Codex CLI @OpenAI | Rust 🦀

Brasil
Joined April 2007
Photo by Felipe Coury 🦀 (@fcoury)Photo by Felipe Coury 🦀 (@fcoury)Photo by Felipe Coury 🦀 (@fcoury)Photo by Felipe Coury 🦀 (@fcoury)Photo by Felipe Coury 🦀 (@fcoury)Photo by Felipe Coury 🦀 (@fcoury)Photo by Felipe Coury 🦀 (@fcoury)Photo by Felipe Coury 🦀 (@fcoury)Photo by Felipe Coury 🦀 (@fcoury)Photo by Felipe Coury 🦀 (@fcoury)
Brasileiro é foda. Vocês dobraram meus seguidores em um dia. 🙏 I can't thank you enough for the support! If you're a new follower, nice to meet you — I'm Felipe. I've been writing code for 30 years (yes, I started very young, do the math gently). 🧵👇
22
9
2
368
40,790
Felipe Coury 🦀 retweeted
Transcript select is in Codex CLI 0.166.0 🎬 Press Ctrl X then [ (like tmux copy mode) and a cursor lands in your transcript. Move with hjkl / w b e, page with Ctrl U/D, jump with / to find, mark with v (V for whole lines), y to copy. Here it is pulling an old repro command back into the prompt. Try it and send me your feedback and sharp edges.
7
4
2
29
4,503
Transcript select is in Codex CLI 0.166.0 🎬 Press Ctrl X then [ (like tmux copy mode) and a cursor lands in your transcript. Move with hjkl / w b e, page with Ctrl U/D, jump with / to find, mark with v (V for whole lines), y to copy. Here it is pulling an old repro command back into the prompt. Try it and send me your feedback and sharp edges.
7
4
2
29
4,503
Felipe Coury 🦀 retweeted
hi all, two things: 1. usage limits are back to being double – your feedback worked 2. we today kicked off an intense sprint to dramatically improve the app simplicity and performance. i will oversee this. more to come. now, send me your complaints
Day 25/ We are doubling all usage limits for all Pro 100/200/500 tiers and Business Premium, effective today. We heard your kind feedback and won’t be reducing usage limits for Pro 200, so your Work and Codex usage will stay the same. We’re also going to continue offering extended limits for dots for now, and usage of your dot will still continue to be separate from your default usage. And we'll of course also keep shipping better models and other efficiency improvements that increase your effective usage over time.
3,824
149
85
5,847
1,728,899
Felipe Coury 🦀 retweeted
Day 25/ We are doubling all usage limits for all Pro 100/200/500 tiers and Business Premium, effective today. We heard your kind feedback and won’t be reducing usage limits for Pro 200, so your Work and Codex usage will stay the same. We’re also going to continue offering extended limits for dots for now, and usage of your dot will still continue to be separate from your default usage. And we'll of course also keep shipping better models and other efficiency improvements that increase your effective usage over time.
7,295
2,637
3,577
38,195
6,220,684
Felipe Coury 🦀 retweeted
Announcing three major scientific discoveries, one each in mathematics (harmonic analysis), computer science (complexity theory), and physics (quantum field theory). AI starting to help us improve our understanding of the universe! openai.com/index/building-sc…
679
2,032
871
16,187
3,178,372
Felipe Coury 🦀 retweeted
GPT-6.1 Terra: delivering fast and capable computer use at a lower price. GPT-6.1 Terra understands what’s on screen, takes action across apps, writes naturally, and is a more capable model for your whole workday with the efficiency to take on more of it.
🤖 Made with AI
1,775
2,506
2,287
28,101
6,796,865
Felipe Coury 🦀 retweeted
Presets are in Codex CLI 0.164.0 🎬 Save the prompts you repeat plus the model, reasoning and other settings you switch between, then recall them mid-task with Ctrl X P or /presets. Here they are in a real review → fix loop. Try it and send me your feedback and sharp edges.
30
19
14
240
41,802
Presets are in Codex CLI 0.164.0 🎬 Save the prompts you repeat plus the model, reasoning and other settings you switch between, then recall them mid-task with Ctrl X P or /presets. Here they are in a real review → fix loop. Try it and send me your feedback and sharp edges.
30
19
14
240
41,802
Also, my first time AI driven video so take it easy. Also, would love feedback on both the preset feature and the video itself 🙃
3
8
823
Felipe Coury 🦀 retweeted
I am proud to be part of this. Going to do a dedicated post about presets and how they can boost your workflow if you change between different models often.
Replying to @thsottiaux
On codex cli updates. We've added reusable prompt presets, inline model and permission settings, and enterprise MCP sign-in. We've also fixed failures when resuming long sessions and added Windows corporate-proxy authentication. Surprisingly the CLI has grown 2X in usage since devday.
5
1
1
51
3,364
I am proud to be part of this. Going to do a dedicated post about presets and how they can boost your workflow if you change between different models often.
Replying to @thsottiaux
On codex cli updates. We've added reusable prompt presets, inline model and permission settings, and enterprise MCP sign-in. We've also fixed failures when resuming long sessions and added Windows corporate-proxy authentication. Surprisingly the CLI has grown 2X in usage since devday.
5
1
1
51
3,364
Felipe Coury 🦀 retweeted
Day 19/ Small updates. Calls connect much faster for dots, changing reasoning in codex & work mid conversation does not invalidate cache anymore and a we've also updated the codex cli.
1,255
225
295
8,312
1,540,744
Felipe Coury 🦀 retweeted
Day 16/ You can now cache for 12h in the API and for logged in users across Codex & Work we keep cache forever and you don’t have any penalty for coming back to an old conversation or resuming after a few hours and are now guaranteed to hit the cache.
You can now choose 12-hour prompt caching in the API. Persistent agents, like dots, reuse context throughout the day. You can keep shared instructions, tools, and context cached longer and pay the lower cached-input rate, even when requests are hours apart.
2,607
682
1,089
15,482
3,141,068
This is a must read aggregate source for the awesome experimentation that's happening in the wild to speed up and improve rust compilation in different aspects.
We're starting to see some agentic Rust forks (or alternative implementations) focused on iteration speed. More-so than the specific projects, I'm interested in the ideas being explored (and how they could evolve upstream), so wanted to collate a few here...
5
797
Felipe Coury 🦀 retweeted
Here’s what we’re cooking with Codex: nitter.cf/i/broadcasts/1RKZzBELB…
306
77
67
1,422
2,005,401
New in Codex CLI v0.163.0: /config. Run it to tweak the experience your way. Check the text selection setting to choose how copy on select works. More coming soon 🙃
4
1
27
1,793
I just love seeing Codex CLI screenshots like this, specially with tables. They have a special place in my heart.
Codex CLI renders Markdown tables beautifully in the TUI. So clean.
1
7
578