
Cooking @byro_ai @agentsimdev
San Francisco, CA
Joined December 2020
- Tweets750
- Following636
- Followers97
- Likes4.4K
Pinned Tweet
I’m building AgentSIM to give AI agents an operational identity.
We’re starting with SMS sign-in for apps you own. You decide what’s allowed; your agent gets the code and carries on.
If you’re building browser agents, I’d love for you to try it.
AI agents need more than tools.
They need an operational identity.
Meet AgentSIM: operational identity and access infrastructure for AI agents.
Starting with policy-bound SMS sign-in for apps you own.
agentsim.dev/?utm_source=x&u…
Fathin retweeted
shipped a free prompt injection test pack. 36 canary probes, point it at any openai-compatible endpoint, get pass/fail
stdlib only bc testing your agent shouldn't need 40 deps 🤡
github.com/Fato07/llm-prompt…
shipped a free prompt injection test pack. 36 canary probes, point it at any openai-compatible endpoint, get pass/fail
stdlib only bc testing your agent shouldn't need 40 deps 🤡
github.com/Fato07/llm-prompt…
asked 12 AI models "what stack should I use?"
62% said TypeScript.
asked "how would you architect it?"
59% didn't name a language at all.
1
2
29
Fathin retweeted
JUST IN: Riemann Hypothesis has been solved.
alpo.ge/remark.pdf
running 3 startups with agents and my job is mostly reading diffs and saying no 80% of the time.
1
3
63
Where does AI intuition come from?
And could machines ever get it?
Taste is the hard part of AI.
It's what we're working on for content distribution at @byro_ai
Fathin retweeted
Where does AI intuition come from?
And could machines ever get it?
Taste is the hard part of AI.
It's what we're working on for content distribution at @byro_ai
MCP is a "standard" and @byro_ai's server just had to learn 3 dialects of it.
we reinvented browser sniffing, but for agents
4
142


