New York, USA
Joined August 2024
Mobile devices have made us give up on designing information systems in human spaces well. Ex 1: looking at the subway platform to find the times of potential transfers should be easier than looking my phone! And nyc is better than many
1
74
How SporeLabs built Cue: a 32M model that catches promises, questions and hand-offs in a live call. Problem, data, labels, proof: SporeLabs did every step. About 28x faster than Jev's API, and it ranked promises and hand-offs more accurately.
2
1
4
93
One giant leap. Three follow-ups. Introducing Cue from SporeLabs. Cue finds every commitment, open question, and hand-off in a call, about 28x faster than calling TypeSafe's Jev. Need a different cue? Tell us what to catch. SporeLabs builds you a dedicated model for it.
1
4
188
I wonder how frequently the conversation fork feature is used in Claude Code et al? Does anyone use it frequently (like relies on it for their typical train of thought)?
1
31
How SporeLabs built Scrub 17M to find more PII than OpenAI's model. 80× smaller than OpenAI's Privacy Filter, more than 30× faster, and it protected more personal data. Public, licensed data. Scaled data assembly. Several designs tried, the best one kept.
1
4
77
Sherlock Holmes could find you from a single detail. SporeLabs Scrub finds and categorizes every personal detail in text: name, address, phone, card, password, API key. Your app decides what to do with it. 17M parameters. 2.1 ms a message on a laptop, offline.
1
4
44
Had a blast at the @OpenAI and @AITinkerers hackathon this weekend. Check out our rough video demo! youtu.be/LgZ7SBqi7Oo?si=SN7R… Potential open source project and better UI dropping soon. Thanks @betaworks for hosting!
1
2
630