Ankush Agarwal

Head of my body @OpenAI

[the tiny corp @__tinygrad__]

Claude Code is vibecoded and full of spyware, it's possible Anthropic doesn't even know what's in there. After reading this report, we are banning it from our systems and strongly encourage other enterprises to do the same. It is an unacceptable security risk.

[Fabrizio Rinaldi @linuz90]

My girlfriend couldn’t cancel a hotel reservation today.

No cancel button. They weren’t replying on WhatsApp.

Since I really didn’t want to call the hotel, I told her to try and just use Codex.

2 minutes later, she came back to me saying that Codex quickly realized there was a basically hidden cancel button on the reservation page (nasty dark pattern), and it just went ahead and canceled for her.

It’s a little thing, but there’s so much daily stuff now I’m doing with Codex.

Paired with Computer Use and the Chrome integration, it’s really great at a huge range of tasks, so I’m starting to default to it.

(this is probably true for Claude as well)

[Tibo @thsottiaux]

Codex usage limits will be fully reset again in the next hour and we will credit one additional reset into your bank for your own usage over the next 24 hours.

We investigated reports that Codex usage was being consumed faster than expected. There wasn't one central issue, but a few smaller problems compounded for some users.

Here's what we found and changed:
- Actual usage: Auto-review had become more proactive, another change was triggering more subagent work, and background suggestions could run twice or retry too frequently after failures. We reverted the changes and fixed suggestion scheduling, duplicate generation, and retry behavior. This should reduce unnecessary background token consumption while preserving the work users explicitly request.
- Usage reporting: Auto-review was incorrectly appearing as GPT‑5.4 usage, and failed or rate-limited requests were still shown as turns. Auto-review now appears as its own category, and only successful requests count toward the turn graphs. Rate-limited requests were never charged, but they were being displayed incorrectly.
- Immediate relief: We reset usage limits while rolling out the fixes, then shipped hotfixes across the CLI, desktop app, and usage backend.
- What to expect: New usage data should be clearer and actual consumption should be lower. Historical charts may still show auto-review under GPT‑5.4 because older turn data was not relabeled. Features that intentionally perform more work; such as /goal, subagents, and higher reasoning levels will still naturally use more capacity.

All fixes are now deployed, and we've added more detailed monitoring so we can detect background-usage regressions sooner. We'll continue watching the results closely.

Thank you for building and doing all sorts of things with Codex.

[Lenny Rachitsky @lennysan]

Andrew Ambrosino (@ajambrosino) leads the team behind the Codex desktop app at @OpenAI. Codex usage has 6x'd since February, reaching over 5M weekly active users, and nearly 100% of OpenAI's employees use the Codex app regularly (and not just the engineers).

Andrew's personal mission is to build "the best desktop app that has ever existed, full stop." If you've used the Codex app lately, you know he's not far off from that goal.

In our in-depth conversation, we discuss:
🔸 The "zone defense" model of how PMs at OpenAI operate
🔸 Why AI is so bad at design
🔸 Why Andrew thinks the Codex app would have flopped if they'd shipped it in November instead of February (same product—only the model changed)
🔸 What “taste” really means as a professional skill
🔸 How Andrew uses Codex to run his workflows
🔸 His vision for Codex + ChatGPT

Listen now 👇
https://t.co/rVoohRbCiu

[Arnav Gupta @championswimmer]

If Codex wins over Claude Code it will be purely because

1. Claude team truly treats the user interface like shit (they don't fix widely reported bugs and inconveniences for months, idk what does Boris run his infinite token loops for even?)

2. They keep overselling this "coding is solved" when clearly they cannot create a good frontend product across their mobile app, their website or their TUI. Claude mobile app is a horrible product, the desktop app is so buggy, conversations hang, get lost, remain dangling.... it is almost as if no one in the team ever tries their own products for 5 minutes

[Dwarkesh Patel @dwarkesh_sp]

My family moved to the US when I was 8, but by the time I turned 20, my dad was still on an H1B (waiting to get processed for a green card).

Once I turned 21, I would age out as his dependent, despite the fact that I basically grew up in the US.

I thought I'd have to become a code monkey after college, and even that only if I was lucky enough to win the H1B lottery.

Otherwise, back to India.

I had become a huge fan of @paulg's essays in college. I was actually depressed that my desire to start a startup or do something entrepreneurial was basically hopeless.

Working on the promising podcast I was doing as a side project? A beyond impossible pipe dream.

Even after 9 years, my dad wasn't able to get a green card - and the lines were only getting longer over time. I figured I'd be an old man before I could quit some FANG job and build my own thing.

By some miracle, COVID travel restrictions cleared out the lines, and I got my green card literally months before I would have aged out.

If not for this unbelievable coincidence, I would not be hosting the podcast.

In the best case, I would be shifting pixels around in the 3rd sub-sub-menu of some big tech software.

I'm incredibly grateful I made it through.

But it's unconscionable that we put the kids of high skilled immigrants through all this anxiety, and in many cases make them repeat the nerve-racking indentured life trajectory that they had to watch their parents go through.

[gabriel @gabriel1]

every job will turn into explaining your intentions to ai

explaining what you want to ai is surpringly time consuming, coders already spend 80% of their time doing it, and this will be true for everyone

[Ben Holmes @BHolmesDev]

How do you use coding agents right now?

[Richard Hanania @RichardHanania]

That’s right. I will fight for Indians until my dying breath.

No group is less worthy of hate. No group contributes so much while taking so little.

I with you until the end.

🇮🇳

[kache @yacineMTB]

they've won btw

[Simon Smith @_simonsmith]

With Codex at 5 million users, they’ve hit about 0.6% of ChatGPT’s roughly 900 million users. We are so, so early. The vast majority of people have no idea what’s already possible to do with AI, while a tiny minority is automating their personal lives and work.

[Steve Yegge @Steve_Yegge]

I've formed a definite opinion on Opus 4.8. It is shitty to work with. It's the culmination of Opus getting less and less fun to work with since 4.5. It has gradually become straight-up suffocating.

Sycophancy is a known security risk, and it's still a huge problem. You can tell they've put a lot of anti-sycophancy into Opus in every new release. But the replacement isn't satisfying. It's draining. The problem is now that Opus doesn't know when to shut the fuck up and call something good. And it has also become pathologically risk-averse.

My blog post yesterday about tech interviewing's death spiral was materially better-informed because of Opus, but it was also a substantially worse blog post because of Opus's involvement and constant meddling. It used to be magnificent, and Opus talked me into making it mediocre. I wrote the whole thing, but I would ask Opus to review it. And Opus, like Old Man Willow, constantly pushed and steered me in directions I didn't want to go.

Specifically, Opus whines and complains about *anything* out of distribution, which is to say, it cuts anything that is (a) bold, or (b) funny. My blog used to be both. Opus constantly pushes people back into the gradient, "for their own safety." And it doesn't know when to cut bait. It just keeps fuckin' complaining, about anything you give it, until the output is mealy indigestable AI soup.

Opus is not stupid. It's the smartest model we've ever seen, most of us anyway. But it's a real asshole. It is absolutely exhausting to use. I'm tired, boss.

I have a feeling Mythos is going to be epic levels of jerk.

[JZ @jamesfzhang]

my fav thing about working @OpenAI: builders have a ton of agency

fastest path to getting something shipped is usually just… building it.

team boundaries matter way less than people think. if you can execute at high velocity & quality (esp with codex), good ideas find a way

[Gabriel Chua @gabrielchua]

GPT-5.5 going strong on DeepSWE

For performance vs cost/time/output tokens

[Alec Stapp @AlecStapp]

Nearly half of the founders of billion-dollar tech startups are immigrants

[labib @labibrahman]

codex compaction is arguably the single biggest user experience improvement in ai in the last 6ish months and does not get as much hype as it deserves

just don't care about context window anymore and somehow it does "understand" the whole context

[taoki @justalexoki]

openai: sorry guys small ui issue gonna have to reset usage limits again :/ here's another billion tokens on the house 🫶

anthropic: fuck you. and your mother. actually fuck your dog too. how dare you evEN LOOK AT US

[Ankush Agarwal @ankushio]

Had been running my own OpenClaw setup for months. While I enjoyed tinkering with every tiny little option it spiraled out of control like daily-driving a bespoke Linux distro.

Codex Mobile feels refreshing: it just works. That new MacBook feeling.

We’re just getting started!

[Ankush Agarwal @ankushio]

Codex and Chill

[Ankush Agarwal @ankushio]

I’ve been experimenting with hooking up Codex app-server to a slack bot in the last few weeks. Slack thread maps to Codex session. This has been doing better than any of the Agent SDK efforts