NolanZZ (@zz_nolan) header
NolanZZ (@zz_nolan) profile picture

Product builder / 蓝勾互关必回

Singapore
Joined October 2025
Photo by NolanZZ (@zz_nolan)Photo by NolanZZ (@zz_nolan)Photo by NolanZZ (@zz_nolan)Photo by NolanZZ (@zz_nolan)Photo by NolanZZ (@zz_nolan)Photo by NolanZZ (@zz_nolan)Photo by NolanZZ (@zz_nolan)Photo by NolanZZ (@zz_nolan)Photo by NolanZZ (@zz_nolan)Photo by NolanZZ (@zz_nolan)
Toggle jump-scare in the apple calendar app
10
44
5,317
kudos to Dot team, this is neat and I think users will like transparency and ability to select model and effort!
12
This was such a fun conversation with @danshipper! My quotes here are more raw than usual. I didn't expect to be quoted, but then when Dan shared this AI-forward interview+transcript idea, I just couldn't say no.
Codex is one of the most important untold stories in the history of technology. A year ago, it was a scrappy effort in a quiet corner of @OpenAI. Its cloud product hadn’t found PMF, and the team was starting over from scratch. Less than 12 months later: - Codex swallowed the flagship ChatGPT desktop app from the inside (it literally runs as com.openai.codex on your Mac) - Codex and ChatGPT for Work hit 40M+ weekly users across engineering and knowledge work - Its leader @thsottiaux was elevated to run all of OpenAI’s core products, including ChatGPT, Codex, and the API How did they pull it off? They trained their own dedicated model line, separate from ChatGPT, with researchers and product builders sitting on the same team They built four different products in a single year (cloud → terminal → IDE sidebar → a desktop app with no code editor at all) as every model leap made a new form factor possible They used Codex to build Codex—so a handful of people could prove a new product in weeks instead of arguing for it in meetings I had a front-row seat to the whole arc—from their failed Cloud launch, to OpenAI’s offices the night before GPT-5 dropped, to the day Codex took over ChatGPT. And I spent months interviewing @gdb, @thsottiaux, @embirico, @mia_glaese, @aambrosino, and @edbayes to get inside how it all went down. Here is the full, behind-closed-doors story of the team that remade OpenAI: every.to/p/how-codex-happene… We’re pushing the boundaries of how stories like this are told. This piece is completely agent-native—designed to be read alongside your agent inside ChatGPT’s in-app browser: - Every interview transcript is included in full: Click any quote and you (or your agent) can see the exact conversation it came from. - Built for your agent to explore: Ask your agent to pull out product lessons for your team, cross-examine the transcripts, or find insights I missed when writing the piece. It’s a story about the future of software—built to be read with an agent: every.to/p/how-codex-happene…
11
2
51
18,466
kudos to Dot team, this is neat and I think users will like transparency and ability to select model and effort!
3
A little upgrade: your dot can now use sign-in codes sent to your connected inbox to log in seamlessly on your behalf. When prompted, you can let your dot use the code once or always allow it to fill in. Lots more sign-in improvements coming soon!
117
53
39
1,183
139,688
kudos to Dot team, this is neat and I think users will like transparency and ability to select model and effort!
4
btw - we've rollout out the ability to connect multiple computers to your dot 💻💻 all part of a bunch of improvements for how dots interact with desktop codex that we are working on. try it out
118
18
8
603
35,209
kudos to Dot team, this is neat and I think users will like transparency and ability to select model and effort!
8
You can now connect multiple local computers to the same dot and choose which one it uses for a task. It can build and test your app on a dedicated machine while you keep coding on your laptop.
684
526
484
7,758
1,595,907
kudos to Dot team, this is neat and I think users will like transparency and ability to select model and effort!
40
Dots can now control many machines in addition to its own little cloud computer that we provide by default.
You can now connect multiple local computers to the same dot and choose which one it uses for a task. It can build and test your app on a dedicated machine while you keep coding on your laptop.
1,575
154
116
5,266
825,756
kudos to Dot team, this is neat and I think users will like transparency and ability to select model and effort!
151
kudos to Dot team, this is neat and I think users will like transparency and ability to select model and effort! @_samirism @sama @thsottiaux
12
Most of you probably haven't noticed this, but dots have a new feature called multi-exec that we quietly released on friday. I've been using it all weekend on my personal dot and it's incredibly powerful. I'd like to share why this is a big deal and how to use it. At a high level, multi exec lets your dot run commands directly on any computer. This immediately turns your dot into a real virtual employee. Here's why it's a gamechanger: - you can attach a powerful machine with persistent storage to your dot (I attached it to my maxed out Mac Studio Ultra) - the dot can now drive your computer directly via Computer Use - this extends to browser use - all your websites stay logged in, residential ip etc - you set up all your CLIs and authentication ONCE and the dot can use them directly (no more fighting the default ephemeral cloud computer) - the dot can save skills locally for repeated workflows and subagents can use those directly - if you have a local obsidian memory vault for your agents, your dot can use that too - building ios app end to end and testing it in xcode, and showing me screenshots of progress as it works - all of the above also applies to any subagents your dot delegates to in the cloud (subagents share context unlike separate threads). To enable it, open the desktop app on your computer and hit "allow computer", then give your dot this prompt: "Hey I just connected my computer. Can you attach to it directly so it's your default computer and you can run commands directly on it? Do it in your root thread so that all subagents inherit this computer for running commands. Run whoami to run water through the pipes and verify it works end to end." I recommend attaching your dot to the most powerful machine you have and investing time into it up front: - Log into all the emails & websites you need e.g. stripe cli, gcloud, firebase, etc - Install and auth all the CLIs, git you need - Make sure computer use is turned on and allowed to use your computer while its locked - I also enabled Allow All for Browsing and Downloads so my dot could use computer use to download whatever it wanted from websites without asking me for approval for each domain (use at your own risk). - Important: I HIGHLY recommend to ask your dot to build out repeated workflows as skills, and iterate to make those skills bulletproof by running water through the pipes with its subagents. As of this weekend, my dot is sending me screenshots of its progress building my iOS app end to end on my Mac Studio Ultra via xCode, and clicking around and testing things end to end. It's able to configure things in stripe via the CLI and use websites when it needs to download images for my workflows. It’s night and day. Don't sleep on it.
252
126
38
2,264
249,620
this is not as good as it might be, internally Dot is routing to Terra which is a terrible model to do technical stuff (real implementation)
1
109
I'm really sorry - but I've been waiting since dev day for this feature and honestly, I've stopped using dots all together because of the constant glitches, crashes, connections errors, safety pauses, etc. It wasn't ready at Dev day and it's not ready now.
You can now connect multiple local computers to the same dot and choose which one it uses for a task. It can build and test your app on a dedicated machine while you keep coding on your laptop.
28
1
1
144
13,688
And they are routing (I.e. forcing) all chat with Dot to the stupid Terra model which make the whole thing unusable now
41
just rolled this out - more dot improvements and fixes inbound.
A little upgrade: your dot can now use sign-in codes sent to your connected inbox to log in seamlessly on your behalf. When prompted, you can let your dot use the code once or always allow it to fill in. Lots more sign-in improvements coming soon!
75
8
3
617
36,133
Do you guys agree this is a stupid workflow? Main reason is that Dot can only send message to a thread created by itself. If i want to start a thread and hand it over to Dot, it is not possible for now.
15
Just did a round table review with the Grok @Bot engineering team. Fixes are being implemented overnight and you should notice a dramatic improvement by tomorrow. If not, reply to this post and we will address any remaining issues right away.
10,300
5,605
1,403
72,888
7,958,270
@thsottiaux @_samirism @sama can you guys learn? I’m paying $200/mo to OpenAI and Dot behave like a freaking retarded. It fails 3 times in a row, countless times within 24 hours. And you still route Dot to Terra? Do you want us to pay Elon instead?
1
26
Every time I read the twitter handle @sama I read it as osama...
31
4
2
309
This is the worst decision. Terra is useless. Can’t get anything done. I won’t be using dot anymore
1
1
27
Totally agree, constantly screw up things
13
Can you STOP ROUTING DOT TO STUPID MODEL i.e. Terra? @OpenAIDevs @thsottiaux @_samirism It is currently in a unusable state and it's so freaking annoying to work with Dot now. See it for yourself, Dot summarized its failures in less than 24 hours. This is not acceptable. #Codex
1
82
Taking a fresh look at @ChatGPT mobile What works well? What takes too many clicks? What would you like to see?
590
17
755
100,149
Dot is unusable now, it repeatedly screw up both technical and non-technical tasks. See the summary from itself. If this is the result you route Dot request to Terra instead of Astra, please stop this NOW, you're destroying this product. I can't work with this level of stupidity anymore. Please report this to the Dot team otherwise I and many users will pay our Pro plan to Anthropic soon.
6
Replying to @embirico
Dot is unusable now, it repeatedly screw up both technical and non-technical tasks. See the summary from itself. If this is the result you route Dot request to Terra instead of Astra, please stop this NOW, you're destroying this product. I can't work with this level of stupidity anymore. Please report this to the Dot team otherwise I and many users will pay our Pro plan to Anthropic soon.
5
Replying to @JamesZmSun
Dot is unusable now, it repeatedly screw up both technical and non-technical tasks. See the summary from itself. If this is the result you route Dot request to Terra instead of Astra, please stop this NOW, you're destroying this product. I can't work with this level of stupidity anymore. Please report this to the Dot team otherwise I and many users will pay our Pro plan to Anthropic soon.
12
Replying to @_samirism
Dot is unusable now, it repeatedly screw up both technical and non-technical tasks. See the summary from itself. If this is the result you route Dot request to Terra instead of Astra, please stop this NOW, you're destroying this product. I can't work with this level of stupidity anymore. Please report this to the Dot team otherwise I and many users will pay our Pro plan to Anthropic soon.
15
Kickstart your weekend build with the new Showcase tab in the OpenAI Developers plugin. Eligible ChatGPT Pro and Business subscribers can claim API credits in billing settings to cover their app’s API usage.
124
60
44
1,056
205,198
Dot is unusable now, it repeatedly screw up both technical and non-technical tasks. See the summary from itself. If this is the result you route Dot request to Terra instead of Astra, please stop this NOW, you're destroying this product. I can't work with this level of stupidity anymore. Please report this to the Dot team otherwise I and many users will pay our Pro plan to Anthropic soon.
8
Would a Pro 50 make sense? Wdyt?
Saw some confusions, but all Pro plans have no 5-hour limits, and give the following usage compared to Plus. ✅ Pro 100 = 10X ✅ Pro 200 = 20X ✅ Pro 500 = 50X, access to ultrafast
4,806
262
556
11,821
2,131,331
Dot is unusable now, it repeatedly screw up both technical and non-technical tasks. See the summary from itself. If this is the result you route Dot request to Terra instead of Astra, please stop this NOW, you're destroying this product. I can't work with this level of stupidity anymore. Please report this to the Dot team otherwise I and many users will pay our Pro plan to Anthropic soon.
1
339
Replying to @thsottiaux
@thsottiaux @OpenAIDevs Can you stop routing Dot to Terra? This is so freaking annoying. Dot fails so hard 3 times in a row and keeps saying “you’re right, I should have xxxx” in the middle of the night and getting technical stuff wrong. If your Dot audience is pure non technical pls send a blog/tweet so we don’t waste our time and effort trying to use it. Terra is just incapable of understanding the tech details and keeps giving BS responses which only make me angry.
9