Vibe coded away my job. AI plumber now - send me your API
USA - Ohio
Joined August 2025
- Tweets376
- Following296
- Followers49
- Likes940
Pinned Tweet
First AgentOS attempt - using enterprise data, so security-first approach. Wired up CoS agent to data table storing each .md as a single row (i.e. soul.md)
Has access to email, To-Do, Planner, Teams, OneDrive, Pinecone memory vector store.
I can chat with it on teams and tell it to update any of its own context or identity documents.
This feels like the easiest and safest way to setup a fully connected AgentOS that runs continuously.
OpenClaw - vulnerabilities
Claude Code, Copilot, Cursor - not autonomous
Claude Cowork - device has to be on, token hungry
Thanks @AIDailyBrief for the template. The idea of AgentOS being platform agnostic is brilliant. I'll take these documents and copy & paste when the leading labs catch up with a secure OpenClaw.
@nlw @AIDailyBrief
The new ChatGPT (work) desktop app does NOT launch for users without local admin access. This is basically everyone in corporate America.
Cluade's desktop app loads without local admin access, but Cowork is greyed out. That's the way to do it.
@OpenAIDevs @thsottiaux
35
These wet lab experiments, where AI takes ideas and optimizes them past human abilities is where we will see crazy change in the next decade.
GPT-5.4 helped drive a medicinal chemistry project from literature review to a validated experimental result.
Paired with Molecule.one’s Maria AI and specialized lab, the model proposed an unexpected way to improve a widely used reaction in drug discovery.
1
40
I've been building n8n workflows for a while now, and the different between OpenAI's GPT-5.4 and GPT-5.5's ability to tool call is profound. GPT-5.5 just gets it, you don't have to spell everything out, idk how they baked common sense into a model, but they did.
Pair AgentOS with GPT-5.5 in n8n and you've got magic
@OpenAIDevs @n8n_io @nlw
34
William retweeted
With the help of Claude Mythos Preview, the Firefox team fixed more security bugs in April than in the past 15 months combined.
My company is hiring. If you're good at IT Security, AI, and want to live in Cincinnati. Apply here:
standardtextile.wd5.myworkda…
2
121
If you haven’t tried n8n AI agents with gpt-5.5, you’re missing out. It’s easier to setup than OpenClaw and it’s enterprise ready if you use their cloud service.
It’s less token hungry because the tasks are well defined. It’s easier to troubleshoot. It has built in data tables. The interface is intuitive. It’s always on. It’s essentially doing my job while I type this.
Don’t wait for Cowork or OpenClaw or workspace agents to catch up. You can build always on AI Agents right now for your job. Use the AgentOS methodology and start building!
@n8n_io @AIDailyBrief @nlw @OpenAIDevs @AnthropicAI @openclaw @sama
1
52
This isn't like a small thing. This is like the o3 reasoning model breakthrough but for network connectivity. Expect new models to scale a lot faster now.
Multipath Reliable Connection (MRC): a new open networking protocol for large AI training clusters, deployed in production on our largest training clusters.
21
Preach
Ilya Sutskever just told the AI industry why scaling is finished.
One word built it. One word is about to break it.
Sutskever: “Scaling is just one word, but it’s such a powerful word because it informs people what to do.”
For five years, that single word replaced an entire research culture.
Nobody needed breakthroughs. They needed bigger checks.
Sutskever: “If you mix some compute with some data into a neural net of a certain size, you will get results, and you will know that it will be better if you just scale the recipe up.”
That’s not science. That’s a recipe.
Sutskever: “Companies love this because it gives you a very low risk way of investing your resources.”
The most transformative technology in human history ran on the same logic used to franchise a restaurant chain.
More locations. More ingredients. Same recipe. Predictable returns.
You didn’t need researchers who could see around corners.
You needed accountants who could approve purchase orders.
But recipes expire.
Sutskever: “At some point though, pre-training will run out of data. The data is very clearly finite.”
Five years of infrastructure. Five years of hiring. Five years of investor decks.
All built on top of something temporary.
Sutskever: “I don’t think that’s true.”
The co-founder of OpenAI. The mind behind the breakthroughs that made this entire era possible.
Saying more money won’t solve it.
Sutskever: “In some sense we are back to the age of research.”
Most of the companies racing to build AGI were never research companies.
They were scaling companies.
They hired for execution. Not discovery. They optimized for throughput. Not insight.
The talent pipelines. The investor pitches. The board decks.
All built around one assumption.
That the recipe would never expire.
It’s expiring.
And the companies that spent five years perfecting the art of spending money are about to discover something.
The next era demands what capital can’t purchase.
An original idea.
1
26
Gemini 4 at I/O is going to be SOTA agentic computer use through Chrome
Google's moat is the 3B-user browser no competitor owns. Native DOM access, Google authentication, autofill, payments.
Anthropic and OpenAI built browser agents on top of Chrome.
Google Gemini IS Chrome.
101
