Max
735 posts
Max
@maximillian_dev
Software Engineer. One day I'll write code that runs on Mars. Views and opinions are my own.
शामिल हुए Mayıs 2021
168 फ़ॉलोइंग97 फ़ॉलोवर्स
Cybertruck what is you doing though fr man
Four parking spots is crazy
Tryna get me canceled fr
Greggertruck@greggertruck
But Cybertruck…. Why would we cut the corner to drive through a random dirt lot though?
English
Actually Smart Summon now reacts a lot faster
Scott Dembraski@SDembraski
I. Love. Smart Summons. I am going to use it as much as I can now. It truly is usable. Here are some examples. Go test it out. I think you will be very impressed.
English
You can now keep codex going for days.
With GPT-5.5 it will build an entire OS kernel for you if you ask, or find critical bugs in a codebase, or optimize your database schemas, or… the options are endless.
Felipe Coury 🦀@fcoury
/goal also lands in Codex CLI 0.128.0. Our take on the Ralph loop: keep a goal alive across turns. Don't stop until it's achieved. Built by my co-worker and OpenAI mentor Eric Traut, aka the Pyright guy. One of the GOATs I get to work with daily.
English
We tried a new thing with NVIDIA to roll out Codex across a whole company and it was awesome to see it work.
Let us know if you'd like to do it at your company!
English
You can use Codex on these plans:
- Plus: $20
-- Go: $8
--- Free: $0!
English
@ryolu_ @cursor_ai Will there be a new version of this? Gpt-5.5? 🤭
English
i use opus 4.7 for planning
composer 2 for building & iterations
codex/gpt-5.4 for hard bugs
all in @cursor_ai
Cursor@cursor_ai
Claude Opus 4.7 is now available in Cursor. We've found it to be impressively autonomous and more creative in its reasoning. We're launching it with 50% off for a limited time. Enjoy!
English
The urge to vague post about what’s coming from the Codex team the next couple weeks is so strong…
I’ll just say that the delta between the internal and external builds of the Codex App is substantial right now 👀
English
@elonmusk @techdevnotes It's ok if it isn't near opus initially as long as it's output is high quality for easier tasks
English
@techdevnotes It will take until May to be close to Opus 4.6 and June to match and maybe exceed. Short time by normal standards, but long time in the AI arena.
English
Grok Build is supposed to be potentially coming next week as per Elon
We still don’t have any clue how competitive it will be to Opus 4.6
Elon Musk@elonmusk
@BasedPresby ~2 weeks
English
@JuanRezzio @cursor_ai Need a way to adjust the branch below the chat without having to open the terminal and manually change it. Also would be nice to select what branch the worktree starts from or what branch the worktree creates
English
Last thursday we released @cursor_ai 3.0!
Are you guys liking it? Is it your go-to coding layout or are you using the IDE?
Curious about your thoughts!
English
@thsottiaux Give users the option to choose a rate plan. Similar to electric pricing where it's cheaper overnight and a little more expensive during the day. Or a balanced plan not restricting core work hours.
English
With Codex the there is quite the gulf in load between peak and off-peak times, and we would like to achieve more of a smoother traffic pattern as that would be a more optimal use of our compute.
We have ideas, but curious what you all think we should do? Would more usage during off-peak and surge multiplier during peak times make sense?
English
@MilksandMatcha I want to build an app to help my team and others unlock our sdlc flow and enable faster time from ticket pickup to deploy
English
Giving away 5 Codex Pro plans
Each person will get 3 months of free Codex Pro (highest tier).
Winners will be selected from comments in 48 hours, comment below why you want it.
OpenAI@OpenAI
Today, we closed our latest funding round with $122 billion in committed capital at an $852B post-money valuation. The fastest way to expand AI’s benefits is to put useful intelligence in people’s hands early and let access compound globally. This funding gives us resources to lead at scale. openai.com/index/accelera…
English
@rohanvarma Would be nice for agents running overnight. I'd like faster models for orchestrating slower ones that can take their time
English
If we made /slow mode in Codex, would you use it? What for?
(Slower inference at a cheaper cost)
English
@thsottiaux What I'm seeing is the need for analytics around ai authored code vs human. There's not a great way to show that today and any benefits or downsides
English
Do people like this? We don't do this for codex because it exists to help you and it's important that you remain the owner and accountable for your work without AI taking credit. At the same time it does mean that you can't trace how popular codex is among repos.
Yuchen Jin@Yuchenj_UW
I noticed something interesting: Claude Code auto-adds itself as a co-author on every git commit. Codex doesn’t. That’s why you see Claude everywhere on GitHub, but not Codex. I wonder why OpenAI is not doing that. Feels like an obvious branding strategy OpenAI is skipping.
English
Some interesting data we pulled today showed that ~40% of Codex users use multiple surfaces, between the App, CLI, and IDE extensions.
Everyone seems to have a primary preference, but a bigger-than-expected chunk of users launch codex agents outside of their primary interface.
If you use multiple surfaces, I'm curious why? And what could we do to improve the experience?
English
@nikgeneburn Would be so useful to my friend and I so we don't play stash management
English
one comment with 0 likes (not hidden) will receive 5 Unheard editions. in 24 hours - touchdown
English
@brandonee916 Haven't had auto on in a long time in cybertruck. Too many dry wipes
English
Am I the only one who Tesla wipers in Auto mode go full speed all the time? I haven’t been able to use Auto for over a year now.
English
@thsottiaux With plan mode being super important, easier ways to read and digest the plans that are made
English