Seba Stavar

4.6K posts

Seba Stavar banner
Seba Stavar

Seba Stavar

@sebastavar

Co-founder @ Halley AI™ — AI Lab + product studio powering Assistants, Insights, Forms, and custom AI. All opinions my own.

Katılım Nisan 2022
272 Takip Edilen394 Takipçiler
Yohei from Japan🇯🇵
Yohei from Japan🇯🇵@learning_yohei·
日本からこんにちは🇯🇵🤭 親愛なるアメリカ人に質問があります🇺🇸🙋 アメリカ人は家の中でも靴を履いて歩くというのは本当ですか?👟😳
Yohei from Japan🇯🇵 tweet media
日本語
5.1K
200
6.7K
264.7K
Seba Stavar
Seba Stavar@sebastavar·
@esrtweet @learning_yohei Wearing shoes in the house is gross. Wearing them in your bedroom is just plain filthy. But shoes in your bed? That’s straight-up caveman behavior.
English
0
0
0
117
Eric S. Raymond
Eric S. Raymond@esrtweet·
@learning_yohei As someone else pointed out, this is variable by region and class in the US. Not wearing shoes in the house is more likely near the coasts and near the upper end of income and class scales.
English
7
2
114
2.9K
Seba Stavar
Seba Stavar@sebastavar·
@HamelHusain Doing what exactly, I have yet to see a single use case that would make me want to waste my tokens on it.
English
0
0
0
352
Hamel Husain
Hamel Husain@HamelHusain·
Seriously stop everything you are doing and use codex desktop app new computer use. Absolutely mind blowing
English
73
63
1.3K
210.8K
SIGKITTEN
SIGKITTEN@SIGKITTEN·
@sebastavar just for posting all the cool stuff it can do that i'm never gonna use
English
1
0
1
34
Seba Stavar retweetledi
Nathan Lambert
Nathan Lambert@natolambert·
I spent some time trying to distill all the complex factors impacting open models -- economics, capabilities, distribution, policy, etc. -- into a clear list of beliefs. Here they are in full. 1. It’s surprising that the top closed models did not show a growing capability margin over open models, based on compute differences for training and research, especially in the second half of 2025 and through today.
English
17
83
907
228.6K
Tibo
Tibo@thsottiaux·
Hi! To celebrate its 1-year anniversary, I have allowed Codex to reset its own rate limits across all plans. Enjoy all the new features.
English
429
154
4.3K
268.4K
Seba Stavar
Seba Stavar@sebastavar·
@Miles_Brundage Yeah, I'm a heavy Codex user, pro plan and all, but these latest features just aren't doing it for me.
English
0
0
0
145
Miles Brundage
Miles Brundage@Miles_Brundage·
Not sure why OAI is framing Codex as being about developers when they're adding a bunch of stuff that developers don't need + which are useful for other people Seems like it's just like, the better ChatGPT app now?
English
24
2
86
7.3K
Seba Stavar
Seba Stavar@sebastavar·
Get real, folks. If you're still wondering why the EU and UK keep missing out on AI features, iOS/macOS capabilities, Tesla FSD, and the like, here's your answer: EU regulations. Bookmark this and check back every time you wonder why.
Angel 🌼@Angaisb_

I think OpenAI should be more open about why certain things don't launch in the EU and UK I don't see why computer use can't come here yet. I'm not saying there's no reason, I just think that when you block features for around 520 million people, the least you can do is be transparent about why

English
0
0
0
51
Seba Stavar
Seba Stavar@sebastavar·
Get real, do they seriously have to spell it out every single time? Let me simplify this for everyone complaining about missing AI features, iOS/macOS limitations, Tesla FSD, etc.: EU regulations Bookmark this and refer to it next time you're wondering why.
English
1
0
0
112
Angel 🌼
Angel 🌼@Angaisb_·
I think OpenAI should be more open about why certain things don't launch in the EU and UK I don't see why computer use can't come here yet. I'm not saying there's no reason, I just think that when you block features for around 520 million people, the least you can do is be transparent about why
English
51
17
384
28.1K
Seba Stavar
Seba Stavar@sebastavar·
This seems important, zero-day vulnerabilities uncovered by Mythos? 🤔
Seba Stavar tweet media
English
0
0
0
10
Seba Stavar
Seba Stavar@sebastavar·
@LLMJunky @thsottiaux I'm sure some will love this, but it doesn't really improve my iPad workflow, I already ssh into my main codex workstation. Might help on iPhone, though. Still regret dropping $1,300+ on that YouTube Pro; should've just grabbed a MacBook Air.
English
0
0
1
79
am.will
am.will@LLMJunky·
A little birdie is hinting at a Codex app for Mobile/iPad. I can't tell you who. Sorry don't ask. OK fine you pressured me. It's Tibo. It's always Tibo.
am.will tweet media
English
38
23
711
47.1K
Seba Stavar
Seba Stavar@sebastavar·
So now I am back at watching my context window with every turn 😶
Seba Stavar@sebastavar

Oops, @thsottiaux fyi ■ Error running remote compact task: { "error": { "message": "Unknown parameter: 'prompt_cache_retention'.", "type": "invalid_request_error", "param": "prompt_cache_retention", "code": "unknown_parameter" } }

English
0
0
0
13
Anthony Morris ツ
Anthony Morris ツ@amorriscode·
Today we're launching a rebuilt version of Claude Code on desktop. The app has been redesigned for the ground up to make it easier than ever to parallelize work with Claude. I haven't opened an IDE or terminal in weeks. Excited for you all to give it a shot!
English
463
236
4.2K
699.7K
Seba Stavar
Seba Stavar@sebastavar·
@MicBryd @cortesi Those are some great tips! I’m using Gemini CLI with Gemini 3.1 Pro for documentation, charts, and other tasks, and an extra review agent when coding with codex.
English
0
0
1
200
Seba Stavar retweetledi
MicBryd
MicBryd@MicBryd·
Gemini 3.1 Pro is trained on Google’s corpus of software architectural greatness. Use the model accordingly. As for Antigravity, use the limited Anthropic rations - antigravity has their own system prompting and agentic strat that pairs well with visual design use cases Use Gemini CLI to leverage Gemini 3.1 Pro for investigations, review, and doc kickstarters.
English
2
1
5
2.4K
Aldo Cortesi
Aldo Cortesi@cortesi·
Yegge gets bodied by Hassabis here, but even to a rank outsider like me a few things are clear: Gemini 3.1 Pro is the weakest of the large coding models, Antigravity is the worst coding harness, and Gemini CLI is the worst CLI. It's an enduring mystery to me why this is.
Steve Yegge@Steve_Yegge

I was chatting with my buddy at Google, who's been a tech director there for about 20 years, about their AI adoption. Craziest convo I've had all year. The TL;DR is that Google engineering appears to have the same AI adoption footprint as John Deere, the tractor company. Most of the industry has the same internal adoption curve: 20% agentic power users, 20% outright refusers, 60% still using Cursor or equivalent chat tool. It turns out Google has this curve too. But why is Google so... average? How is it that a handful of companies are taking off like a spaceship, and the rest, including Google, are mired in inaction? My buddy's observation was key here: There has been an industry-wide hiring freeze for 18+ months, during which time nobody has been moving jobs. So there are no clued-in people coming in from the outside to tell Google how far behind they are, how utterly mediocre they have become as an eng org. He says the problem is that they can't use Claude Code because it's the enemy, and Gemini has never been good enough to capture people's workflows like Claude has, so basically agentic coding just never really took off inside Google. They're all just plodding along, completely oblivious to what's happening out there right now. Not only is Google not able to do anything about it, they don't seem to be aware of the problem at all. I'm having major flashbacks to fifty years ago as a kid at the La Brea Tar Pits, asking, "why can't they just climb out?" My Google friend and I had this conversation over a month ago. I didn't share it because I wanted to look around a bit, and see if it's really as bad as all that. I've been talking to people from dozens of companies since then. And yeah. It's as bad as all that. Google is about average. Some companies at the bottom have near-zero AI adoption and can't even get budget for AI. They may have moats and high walls, but the horde is coming for them all the same. And then there are a few companies I've met recently who are *amazingly* leaned in to AI adoption. One category-leader company just cancelled IntelliJ for a thousand engineers. That's an incredibly bold move, one of many they're making towards agentic adoption. In my opinion, that company is setting themselves up for a _huge_ W. As for the rest, well, it's the Great Siloing. Everyone's flying blind. With nobody moving companies, no company knows where they stand on the AI adoption curve. Nobody knows how they're doing compared to everyone else. Half of them just check a box: "We enabled {Copilot/Cursor} for everyone!" Cue smug celebrations. They think this is like getting SOC2 compliance, just a thing they turn on and now it's "solved." And they don't realize that they've done effectively nothing at all. All because of a hiring freeze.

English
22
8
351
48.2K