Building something new. Prev head of eng @CoinbaseDev, @ourzora Creator of https://nitter.cf/t.co/IPSb3wfr2S
The Internet
Joined July 2011
- Tweets3.1K
- Following1.8K
- Followers15.9K
- Likes14.6K
Replying to @garybasin
20/15 got lasik
I'll publish a bunch of writing on what the vision is in a few weeks when the beta launches.
Replying to @DavideCrapis
muse is I think best in class right now
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
Replying to @SalvatoChris @mewwts
Maybe I should give it another shot. I use Orcas remote orchestration a lot which cmux didnβt use to have.
Kind of. I use Claude and codex hosted on a remote dev box (exe.dev) with schedules and the ability to ping me when Iβm away. When Iβm working (most of the time these days) I access that dev box via orca and typically have 3-5 sessions running.
Itβs kind of an emergent personal assistant harness customized to how I like to work.
Replying to @0x_Osprey
For technical people I think thereβs extremely high value in customizing for exactly what you need
Replying to @mewwts
Orca is kind of like a terminal multiplexer with a browser built in, I use via cli through orca
Replying to @mewwts
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
erik.eth π‘ retweeted
The spec for lightning in x402 was merged last night!
github.com/x402-foundation/xβ¦
impressive result on JevBench
Replying to @marco_derossi
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.
The internet is so underrated. Theres no chance we would have ended up with AI without the open web.
Replying to @Must_be_Ash
@Must_be_Ash does it again
so sick!