Micah Rairdon
986 posts
Micah Rairdon
@tiberriver256
Loves God, family and anything to do with technology!
allendale, mi Katılım Ekim 2010
1.1K Takip Edilen55 Takipçiler
jesus gpt 5.5 on codex on high thinking compacts all the time
English
Microsoft is deploying OpenAI's frontier GPT-5.5 model across its entire enterprise ecosystem, including GitHub Copilot, M365 Copilot, Copilot Studio, and Foundry, bringing its advanced reasoning and multi-step execution directly to daily workflows.
Satya Nadella@satyanadella
Super excited GPT-5.5 is rolling out to GitHub Copilot, M365 Copilot, Copilot Studio, and Foundry today. With deeper reasoning, stronger multistep execution, and better performance across long, complex tasks, GPT-5.5 helps you go from idea to execution faster with fewer iterations to get to the right outcome. It’s all about helping you choose the right model, or models, for the right task across your workflow.
English
Micah Rairdon retweetledi
Are there good human-curated skill repos for design, coding, product, etc that's not "here's 100 skills you separate the slop yourself"
English
@sama The perf on it is crazzzzzzy bad though... 30s of a locked up sign in screen before it shows that it's beginning to load models then 60s of a locked up screen before I can type...
Very vibe coded
English
how can they write code so fast?!
henrique cunha@henrycunh
codex app is trending to be the best software i've ever used ridiculous how fast it got so good
English
Developers, you have $20.
What are you buying ?
-Claude -Codex
English
@droidbuilds Move to OpenAI sub...
Use pi.dev..
🧙♂️🧙♂️🧙♂️
English
An alarming amount of production software upon which civilization depends looks just like this.
Science girl@sciencegirl
Since 2005, architect Keisuke Oka has been personally constructing this structure in Tokyo without using any blueprints. The project is still ongoing and is expected to take as long as 200 years to fully complete.
English
English
@github @acolombiadev Now if only we could figure out why you're jacking up the prices...
English
With the GitHub Copilot SDK, you can add the same AI that powers Copilot Chat to your own applications.
To test this out, @acolombiadev integrated the Copilot SDK into a React Native app to generate AI-powered issue summaries, with production patterns for graceful degradation and caching.
Here's how she did it. 👇
github.blog/ai-and-ml/gith…
English
@petergyang *Googles "threads"*
...
*Remembers googling is now a sign of being old*
English
People on X:
“Looks fun, do a barrel roll!”
People on Threads:
Peter Yang@petergyang
Asked GPT 5.5 and Codex to make Star Fox. This is after 15 min of prompting 🔥
English
Ya'll GPT 5.5 produces wayyyyyy better code than 5.4. I've been using it on high and I am impressed so far.
David Fowler@davidfowl
There's a really high cost of duplicating code and we're all relearning that everyday with these coding agents. Until they get better at generating reusable code, bugs will run rampant. You can't "abstract it away" with more agents. You just get crappy software....
English
@davidfowl Put it on low...
Then run it with thinking off...
So funnnn
English
@Angaisb_ The fun part is you can get Opus 4.7 intelligence from gpt5.5 low
English
@vennictus @_watzon I've been having great success with low and thinking disabled even
English
My quick review of GPT-5.5 on Codex Plus (so far)-
This thing is absolutely insane and sneaky.
I’m not a “prompt and forget” type of user - I actively monitor what's happening while working on my personal projects.
Up until now, I was running GPT-5.4 on xHigh and High. It was already tight - I’d usually get only about 3-3.5 hours of solid usage within the 5-hour window before hitting limits.
Today I switched to 5.5 xHigh… and I completely burned through the entire quota in just one hour. At first I thought something was broken, so I stopped, did the math and checked the code. Turns out, in that single hour, 5.5 had written more than what 5.4 had given me in 2 * 5h sessions and managed to find serious flaws in its work. Part of me now wants the $100 dollar plan and just let it rip!
English
@thsottiaux If only the desktop app didn't constantly freeze up 😔
English
@thsottiaux Codex desktop app perf is crazzzzzzzy bad. Many GitHub issues on this for Mac too.
Once you are able to type into a prompt it's okay but getting there is a journey of frozen/nonresponsive screens.
English
@NathanMcNulty I'm not sure about what promises they made but I like to look at this particular bench which is tokens needed to complete the benchmark. Decent drop vs 5.4 on XtraHigh and the low/non reasonings are insane relative to other models.
#output-tokens-used-to-run-artificial-analysis-intelligence-index" target="_blank" rel="nofollow noopener">artificialanalysis.ai/models?models=…
English
@tiberriver256 I don't know that I believe the promises of it being that much more efficient, but it should have been a 3x at most
English
i don’t understand people still using claude code when codex exists
English