Pinned Tweet
Low key embarrassing to be someone driving Codex Desktop development at @OpenAI, with such capable agents and models, and still unable to do use them to do the most basic of software engineering tasks like bug report triage / fixing; when half of them are pre-investigated anyway.
Replying to @M1Astra
It's actually low key kind of sad/pathetic tbh.. like, in a traditional software dev environment I could respect the time it takes to fix bugs/etc; but with an army of highly capable AI agents at hand, and with users filing far more detailed bug reports (and often solutions) [..]
Glenn 'devalias' Grant retweeted
Coming soon to a ChatGPT app near you! Don't lose progress, even after restarting the app.
Glenn 'devalias' Grant retweeted
AI agents are writing more code. How can developers ensure that code is correct?
Microsoft Research’s Proof-Driven Development (PDD) Kit explores a more rigorous approach: it translates a developer’s intent into a formal specification, then uses formal verification to prove that generated code meets it.
PDD Kit works with Verus for Rust and is integrated with @GitHubNext’s Chopin, bringing formal methods into an AI-assisted development workflow for teams.
See the work in action at @github Universe, Oct. 28–29, 2026.
Glenn 'devalias' Grant retweeted
How do you _guarantee_ your agent's code is correct? You prove it.
Introducing Proof Driven Development Kit (PDD Kit) from @MSFTResearch.
PDD Kit helps turn your plan into a formal spec, then proves the agent's code meets that spec for every input. No vibe verification. PDD Kit is integrated with @GitHubNext's Chopin, so you can plan as a team.
PDD Kit takes an app's login flow from intent to a verified pull request:
It discusses your code, infers your intent as it goes, and proposes a formal spec in Verus, a proof language for Rust.
Once you approve the spec, the Verus verifier automatically proves the code meets it.
Where proof isn't possible, it falls back to empirical verification with tests and computer-use agents (CUAs).
It works on Rust today. No new language, no change in how you produce the underlying code, making formal methods more accessible.
The goal is a verified software factory, where engineers review specifications instead of code.
Come see it in action at GitHub Universe, Oct 28–29. Swing by the Speakeasy and ask for GitHub Next!
Saw this Beeper <-> ChatGPT Dots integration pop up on GitHub the other day and been watching it's development/integration waiting for this announcement!
That feel when @OpenAI Codex bugs/issues burn ~42-80 hours of your life (not counting lost productivity/opportunity cost/etc) on a whole pile of bugs and performance issues that could have been triaged and fixed SO much sooner if they were actually prioritised.
Replying to @_devalias @ajambrosino
Then looking at my time tracking:
> The strongest figure is 42 hours 47 minutes logged against explicit Codex-related troubleshooting, across 138 entries on 34 dates. Including recovery tools and workflow work brings it to 80 hours 34 minutes, after removing overlapping timers.
That feel when @OpenAI Codex bugs/issues burn ~43.6 agent hours and ~48.7 million uncached tokens (~1.08 billion tokens including cached) on a whole pile of bugs and performance issues that could have been triaged and fixed SO much sooner if they were actually prioritised.
Replying to @_devalias @ajambrosino
> The selected threads account for approximately:
>
> - 43.6 hours of recorded agent runtime after removing overlap—46.3 hours summed.
> - 48.7 million uncached input/output tokens.
> - 1.08 billion input/output tokens including cached context.
Glenn 'devalias' Grant retweeted
codex desktop complaints, go
Glenn 'devalias' Grant retweeted
Get in your feedback on how to make the @ChatGPT app better!
If you’re using plugins in the app, tell me:
- How can we make the experience simpler?
- Where are the bugs?
- What are the paper cuts that just build up til you rage quit?
Glenn 'devalias' Grant retweeted
Send me your Sites complaints
Glenn 'devalias' Grant retweeted
Introducing autoresearch for arXiv papers
Change "arxiv" to "autoarxiv" in any paper URL
OpenResearch creates a project for you, sets up an environment on your preferred compute, and runs a minimal reproduction. The agent tracks logs, visualizes runs, and produces artifacts all in a closed loop, entirely local. See more below 👇
Let's see how this intense sprint to dramatically improve app simplicity and performance goes... I wonder how many of the 25,434+ reported Codex GitHub issues will be triaged/de-duplicated/fixed as part of this... 🤔
github.com/openai/codex/issu…
Replying to @_devalias @OpenAI @ajambrosino @thsottiaux @embirico @simpsoka @edbayes @romainhuet @derrickcchoi @Dimillian @pvncher @matteing @dkundel @nickbaumann_ @ah20im @acrognali @pakrym @trekedge @DerekFeriancek @JamesZmSun @SIGKITTEN @fchalissery @gmcharmander @TheRohanVarma @coreyching @fcoury @EMostaque
Or not naming windows usefully....
nitter.cf/_devalias/status/20641…
Replying to @_devalias @thsottiaux
Also, naming the windows based on the thread they have open, so I don't have to manually sift through 13 different 'Codex' windows to try and and guess which one was the one I actually needed.
Not to mention Codex / ChatGPT still not having first class support for Apple reminders/calendars/etc
nitter.cf/_devalias/status/20515…
















