Writing about Vibe Coding and AI on X. https://teapaw.org/t.co/OE3ilaesDe https://teapaw.org/t.co/Tu7JTKUnHJ
Japan
Joined June 2026
- Tweets833
- Following183
- Followers105
- Likes407
Pinned Tweet
Monday again with OpenAI.
- Sol 5.6 High effort till 40% of the weekly limit left
- Sol 5.6 Medium till 15% left
- Luna after?
Hoping for some reset along the way.
How do you use your models?
A few weeks with @bot
Amazing: I literally can build small interactive textual apps that evolve over time just with a few commands
Horrible: the task scheduler does not work at all. At all. Fires at random times, when it fires. Or gets stuck.
After asking repeatedly the Chief bot to fix it, it decided the only way was to message all other bots at random times to remind them to fire scheduled tasks. Result: weekly limit reached in a night
I know I’m late in saying that but @bot is so impressive
My first impressive use case: ask me every 30 minutes to translate a sentence from English to Japanese, and correct my translation
As the time goes, I ask it to make it more difficult, or to focus on a particular situation, or to ask me another sentence using a similar expression I want to learn in 3 days
And it just works. Easy to imagine how a chat can just morph into a full blown language learning app just be using it over time
And for 20$ a month
The big mind shift for developers in the AI age is
- to stop caring about the quality of the code produced
- and start taking pride in the quality system we build around our tools to allow them to evolve it faster than ever.
OK, more experience with Codex /fast and... it does not make any practical difference right?
Anyone see ay difference?
The proverbial quality of Apple software.
Mac OS App Store install dialog... only has a Cancel button
apple.stackexchange.com/ques…
Unexpected gains from using @WisprFlow : speaking faster
I was stunned to see someone's Wispr Flow Insights showing he was speaking at ~190 words per minute (and I was just at 100wpm!!)
I focused on improving that, and a few weeks later I already speed up by 28%!
One way I learnt to improve the quality of AI output are adversarial tests
- Ask Agent 1 to produce something
- Tell Agent 2 to assume the product of Agent 1 is an hallucination or prove that it is correct
This seems to work much better than "testing if Agent 1 work is correct"
Read the code VS Test the code
In the 26+ years I worked in IT, we always reviewed the code. Every commit, in every company.
Testing, on the other hand, we could have always done more.
More adversarial testing, more negative test cases, more integration, more end to end, more frequent performance and load testing.
But there was never enough time.
That's how I see the read the code vs don't read the code debate.
AI allows us to create the most extensive test suites we have ever had; it allows us to modify tests quickly when we change the code. It allows us to create new test environments quickly
and ultimately allows us to not read the code
I haven't had time to play video games for decades, but I recently realized the probably obvious thing of how AI can make video games modding and tinkering explode
Decompiling data files, save files, skins, and making all kind of changes
Is this actually happening in gaming communities?
I mentioned I could switch from Claude Code to Codex within a day, but if I put back my CTO hat, that's not sustainable.
As a company, you can't chase every quarter the best model, and ask all engineers to switch to it all their customization and skills.
This is a harder problem to solve than it looks like. On the surface, /skills are easily transferrable, but the reality is that every model will interpret (or ignore!) instructions in a different way
Your AI provider choice is definitly more sticky then one could think
Phil retweeted
It's me again. I come bearing great news.
First of all, we have hit 20M active users for Codex some time this week. Second of all, this is cause for celebration and during the day we will credit every Codex and ChatGPT Work user with a BANKED reset that you can use at your own leisure. And we will have some other good news later too!
Now, on usage limits draining faster, while we're not seeing anything abnormal, we do take it incredibly seriously and there is an ongoing investigation. I will share if we do find anything and my below post is really a clarification on a specific pattern that we did see that I wanted to call out.
Go do something amazing today.
We've investigated a few messages about codex usage limits being different. That's not something we change without engaging the community and being transparent.
What we did see is that when talking to affected users many were using sub2api. Converting a subscription into api traffic to then re-serve or share across many users is not something we support and this type of usage gets flagged by our fraud-prevention systems.
You are completely fine if you use your subscription through Sign in With ChatGPT, either through the official clients or through one of the many OSS clients (Pi, OpenCode, ...) that support signing in with your account and using your included usage.
A few months of intense AI coding in, how am I doing at the kind of aggressive, intensive handling of 4-8 Codex sessions simultaneusly?
I'm getting better honestly. A couple of tricks:
1. I scribble down, on paper usually, what each agent is doing, so I don't lose track
2. I alternate between coding mode and merging mode. I start 3-4 coding agent in parallel (coding mode), wait for all of them to finish, and the test each agent work and merge it (merge mode)
If AI allows you to create way more tests than you ever had the luxury to create (unit tests, integration, e2e, load tests, performance tests, security)...
... does it matter if you don't read the code?
Today we are thanking Adobe for making their crap so hard to remove from your computer that you need to install an "Adobe Cleaner App"
That's all for me trying Hermes.
The UX is just terrible.
I tried it the first time a month or so ago, my cron jobs would work for a couple of days and then fail
This second time, after being able to install it *with a lot of erros and asking ChatGPT for scripts to fix it*, I got it working. Desktop App running on Mac, with remote gateway and agents running on a VPS:
- The remote agent would work the first time
- The second time can't load the session
- And the session is exactly 1 question
Known bug from a month ago, never fixed
github.com/NousResearch/herm…
2 hours to the reset line, I'm running Sol 5.6 on /fast ... but honestly I was expecting a more noticeable performance improvement... disappointed
Hermes Bot finally set up
For people saying "How can people not use agents"?
- Hermes installation failed multiple times (on Ubuntu)
- I needed ChatGPT to create scripts to install Hermes
- I could not install the remote desktop app only on Mac. I had to install the full Hermes locally, and then ignore it and ask to connect to the remote agent
Successful apps do care about UX over everything else
WHAT!
Nobel prize, right now
(too bad I don't have a Claude subscription anymore)
