Alex Schüren @am29d

Solutions Engineer @OpenAI Germany Joined May 2013

Tweets

1K
Followers

629
Following

1K
Likes

7K

Alex Schüren @am29d

3 weeks ago

Friendly reminder that you should write loops. Are you looping already? Stop whatever you are doing and start writing loops.

0 0 0 17 0

View Details

Alex Schüren @am29d

3 weeks ago

still unsolved, but imagegen (with good set of skills) comes close

I’ve been hunting for a way to get agents to produce consistently good diagrams - are there better options? * Mermaid: tired of the awful layout algo * drawio: the model can't seem to reason about the XML, even with a skill * Diagrams library has nice results, but you have to

21 5 89 15K 141

0 0 0 19 0

View Details

Alex Schüren @am29d

3 weeks ago

@thsottiaux This needs to be also semantic search, similar how vercel has it in their console, pretty please, sending tacos 🌮 🌮 🌮

0 0 0 59 0

View Details

Andrew Ambrosino @ajambrosino

4 weeks ago

install codex on your parents’ computers so you can fix stuff remotely

212 121 4K 224K 284

View Details

Andrew Ambrosino @ajambrosino

4 weeks ago

59 17 748 34K 41

View Details

OpenAI @OpenAI

4 weeks ago

Building apps has never been easier. With Sites, Codex can turn your work, ideas, and plans into an interactive website or app your team can explore, use, and share with a URL. Rolling out to Business and Enterprise plans, before expanding more broadly.

969 2K 20K 9.6M 10K

View Details

Alex Schüren @am29d

a month ago

We are slowly converging to the point where you no longer need to click around.

Francis Chalissery @fchalissery

a month ago

Small QoL improvement in today’s Codex App update: you can now search through all prior chat content to find past threads!✨

16 12 172 74K 38

0 0 0 53 0

View Details

BOOTOSHI 👑 @KingBootoshi

a month ago

WOW I did not expect these results. This is actually crazy, insightful, and completely changes my dev workflow moving forward: A SINGLE CODEX /goal RUN IS THE CLEAR WINNER. NO ORCHESTRATION, NO OUROBOROS, JUST ONE LITTLE AGENT THAT COULD 🤯 IT COMPLETELY DESTROYED THE OPUS ORCHESTRATOR IN SPEED AND QUALITY! Before I went to sleep, Codex 5.5 xhigh finished 1 hour in! Full migration done, everything clean. I reviewed the PR and I am very happy. Claude Code (Opus 4.7) was working for 5 hours at that point by the time I went to bed. I woke up, and it's still working! 13 hours! It actually stopped working because it stopped to ask me an irrelevant question. Orchestration has never took this long for me in the past. I'm using the new CC /goal mode and auto-compacting at 25% (250k context) to prevent context rot past that point It is STUPID SLOW (which is funny bc it's managing GPT 5.5 low, fast-mode, so it shouldn't take THAT long) for what ended up being LOWER quality work! By a mile! This was really surprising to me, because before 5.5 came out Orchestrating like this was the absolute best, fastest and most efficient. And now on a large critical task, it was more than 6x slower than a single 5.5 /goal mode instance on xhigh ??? It seems compaction played a large role in the slow down here here, because Claude Code compacts at 25% (250k tokens) automatically (I set this in settings) Everytime it compacts it has to take the time to READ EVERYTHING and then get the full context then execute and get full again then compact and oh boy it's not efficient at all. In fact, most of it's time as the orchestrator was spent compacting and reading context then compacting again! Then Codex would just have one long continual running compaction, and just kept moving forward. I believe my goal ledger skill plays a big role in helping it stay aligned here! Look at this difference LMFAO: - Codex PR #23: backend Supabase removal complete, canonical wake wired, preserved surfaces intact, typecheck/lint/tests green, dogfooded against local Postgres, one item correctly deferred + documented. Mergeable now. +4,056/−981. - Claude attempt-1: fails the headline goal (supabase dir + 9 importers still present), regressed a preserved surface (gutted task.service, stubbed tasks.router to emptyBoard — PRD-forbidden), deleted ~5,456 test lines, uncommitted/dirty. The 17,762 deletions are over-deletion, not more work. Wow. I am actually shocked. I am so happy I ran two diff workflows on a big, identical PERSONAL problem. This completely changes my workflow moving forward- no longer will I orchestrate a big task from the top down Instead, I am going to now experiment with the following flow on Codex: 1. Having Codex scope our codebase, then having. aback and forth brainstorming/discussion on what needs to be done 2. Creating a master PRD from that file, and SPLITTING the work into focused branch work 3. Branching off the chat in parallel, until we get to a part where we need to merge work, then parallelize again This way, Codex agents can work individually, every single branch will have the same research/brainstormed context, and they just work to full completion Based off this experience, this feels like the right direction. I will never do an orchestrator in this style again (executing a PRD to completion). Instead, I will do more of... a manager of branched work. Regardless of what I do moving forward, I will never run an orchestrator setup like this again. LMFAO

BOOTOSHI 👑 @KingBootoshi

a month ago

OK FIRST EVAL: CODEX RUNNING /goal VS. CLAUDE CODE ORCHESTRATING CODEX AGENTS I have an ACTUAL long form tasks I have to finish. I created two separate worktrees This one is a full migration of services from Supabase to self-hosted Postgres instead, dogfooded, e2e tested I

27 2 199 54K 114

39 24 325 38K 209

View Details

Alex Schüren @am29d

a month ago

@aditiitwt Ask Codex

0 0 0 13 0

View Details

Alex Schüren @am29d

a month ago

Justin is a machine. I once ranted about some tiny thing I thought nobody would care about, and he pinged me right away and fixed it like it was nothing. Send him your weirdest bugs.

Justin @JustinBleuel

a month ago

Every bug in @ChatGPTapp is getting fixed With the help of codex (and the rest of the lovely team and their codexes) along with a 7pm iced americano there will be zero bugs This is a formal request for tiny nits, error states, broken ui, etc The tinier the better!

721 47 790 409K 104

0 0 0 59 0

View Details

OpenAI Developers @OpenAIDevs

a month ago

We’re having way too much fun working through your feedback. (Please, keep it coming.) Keyboard shortcuts are now customizable. Set Codex up around how you actually work, then tweak shortcuts from settings instead of adapting to our defaults.

294 153 2K 480K 376

View Details

Alex Schüren @am29d

a month ago

@thsottiaux We need more shortcuts, git commit, push, I want to disable my cursor inside Codex.

1 0 0 34 0

View Details

Zed @zeddotdev

a month ago

You can now use your ChatGPT subscription in the Zed agent, with the same usage and rate limits you benefit from in Codex directly. We're grateful that @openaidevs continues to support subscription-based access for third-party tools, even as others move toward usage-based billing.

146 219 4K 446K 543

View Details

OpenAI @OpenAI

2 months ago

You've been asking for this one... Now in preview: Codex in the ChatGPT mobile app. Start new work, review outputs, steer execution, and approve next steps, all from the ChatGPT mobile app. Codex will keep running on your laptop, Mac mini, or devbox.

2K 3K 22K 5.0M 5K

View Details

Theo - t3.gg @theo

2 months ago

For every person who replies with a screenshot of their cancelled Claude Code plan, I will donate $10 to open source.

Theo - t3.gg @theo

2 months ago

I can't help but feel personally burned by the Claude Code changes announced today. We put so much work into wrapping the (atrocious) Claude Agent SDK in T3 Code. It was the ONLY path they supported, so we made it work. It was hell. Now our users are getting their rate limits