Building something new. Prev head of eng @CoinbaseDev, @ourzora Creator of x402.org
The Internet
Based in North America
- Tweets 3,111
- Following 1,815
- Followers 15,825
- Likes 14,666
20/15 got lasik
I'll publish a bunch of writing on what the vision is in a few weeks when the beta launches.
1
7
367
I'm still in stealth, but I'm hiring!
Location: SF preferred, but remote in North American time zones is possible for exceptional candidates.
Open roles
- Founding Engineer: build stuff
- Founding Product Marketing Manager: grow stuff
We offer generous salary, equity, health care, and the opportunity to work with smart and kind people on meaningful problems to help advance the state of agents.
How to apply:
Email jobs @ 5d.tech with:
- LinkedIn / X / GitHub / Resume / Personal site / etc
- A description of the thing you've built you're most proud of
- Your current favorite product & why you like it
- Your all time favorite website
- A good meme
49
20
469
67,650
Maybe I should give it another shot. I use Orcas remote orchestration a lot which cmux didn’t use to have.
2
1
114
Kind of. I use Claude and codex hosted on a remote dev box (exe.dev) with schedules and the ability to ping me when I’m away. When I’m working (most of the time these days) I access that dev box via orca and typically have 3-5 sessions running.
It’s kind of an emergent personal assistant harness customized to how I like to work.
2
100
For technical people I think there’s extremely high value in customizing for exactly what you need
1
5
192
Orca is kind of like a terminal multiplexer with a browser built in, I use via cli through orca
1
2
107
I use claude / codex pretty much evenly, both through Orca, personal assistant agents I try them all but haven't found myself reaching for any
2
1
187
erik.eth 🛡 retweeted
The spec for lightning in x402 was merged last night!
github.com/x402-foundation/x…
26
52
234
100,286
impressive result on JevBench
On JevBench, Sage1 scores better on accuracy than other System1 models, with a similar median latency.
When multi-step reasoning is required, Sage has 93% accuracy vs. 71% for other System1 models.
Sage is smart enough to know when to be fast and when to think step by step, covering both System1 and System2.
When Sage activates reasoning, it takes on average 3X longer to decide.
6
1,984
more options good
So far the minimum viable unit of economics on the internet has been ~$5. I suspect thats not the floor of what something can be worth in a market.
We shall see, experiment still in progress
1
12
1,157
The internet is so underrated. Theres no chance we would have ended up with AI without the open web.
11
1
54
3,426
@Must_be_Ash does it again
so sick!
I pay tested thousands of x402 endpoints and I'm open sourcing the whole thing
think OpenRouter for tools meets n8n, served over plug-and-play MCPs
> you get a catalog of 2,000 services
> a visual workflow builder
> spend controls
> connect to Claude or ChatGPT with oAuth
8
3
53
5,841
Agents are like water, they’ll flow to whatever solution is easiest
Just had my first organic agentic x402 magic experience
• Needed my agent to access a website for which I didn't have an account.
• It discovered (on its own) Apify, which accessed that service on its behalf. Apify accepts x402 payments, which is what my agent then suggested
• Agent set up its own wallet (it has never done a crypto tx before), gave me a deposit address on Base. I sent it some USDC (and no ETH)
• Agent then connected to Apify on its own, arranged payment via x402, and got the data it needed, reporting it back to me.
The whole sequence involved just 4-5 single sentence prompts from me. That was all pretty magic, but then I asked it this question.
Agentic commerce on crypto rails is the future.
agent was pi agent
model was kimi-k3-fast-api on venice.ai/api
15
6
107
10,173