Ryan Lin (@_ryanlin10) profile picture

Building, Physics & Philosophy @ Oxford, IOAA Gold

Oxford, England
Joined November 2022
Photo by Ryan Lin (@_ryanlin10)Photo by Ryan Lin (@_ryanlin10)Photo by Ryan Lin (@_ryanlin10)Photo by Ryan Lin (@_ryanlin10)Photo by Ryan Lin (@_ryanlin10)Photo by Ryan Lin (@_ryanlin10)Photo by Ryan Lin (@_ryanlin10)Photo by Ryan Lin (@_ryanlin10)Photo by Ryan Lin (@_ryanlin10)Photo by Ryan Lin (@_ryanlin10)
Luke and Avi are incredible, they held conviction on the bet on duplex voice models long before it was mainstream, check out their work
Introducing Interact-0, the first in a new generation of always-on models. Interact-0 is a full-duplex speech model designed around human interaction. It is the only model that knows when to speak in groups, and can be active without barging in when it shouldn’t. We share our thesis, approach, and early results below. interact.inc/blog/interact-0…
7
356
A very interesting area of research! The future of voice interfaces requires a large amount of visual understanding as well Both will come hand in hand
Introducing Orion, a foundation model that predicts where you look. Orion finds twice as many UX bugs as frontier models, cuts computer-use latency by 31%, and even won a drone race.
1
1
3
414
Introducing Orion, a foundation model that predicts where you look. Orion finds twice as many UX bugs as frontier models, cuts computer-use latency by 31%, and even won a drone race.
57
95
19
2,022
68,494
Orion resembles human behaviour and can spot the odd one out. Predicted gaze concentrates on a misplaced shoe, female duck, pink blossom tree, and red leaf.
1
27
1,853
Orion prevents computer-use agent prompt injections. We reduce attacks 96% by flagging messages that appear in areas with low predicted gaze density.
2
20
1,679
You can plot a straight line on the METR plot within error bars
1
2
695
Be careful vibe coding guys
297
Free doughnut method for GTM has officially been patched
264
We are releasing an open-source pipeline to predict your user sentiment from computer actions Connect to your existing session replay tool Prevent loss of signal with high-fidelity mouse capture Pick refined recipes to train sentiment models on your user data Check it out: paradigmmachines.ai/orion
6
8
606
Our keystroke data collection is privacy-preserving, capturing timing (press and release timing) rather than content
17
Synthetic sentiment labelling with VLMs allows us to push past previous data walls VLMs can label based off semantic (prompt) and visual (UX) context
22
The issue with sentiment classification is there hasn't been enough labelled data to do it at scale Sentiment classification demonstrates log linear scaling
182
Why do these guys keep reaching out to me
1
1
5
1,020
claude was probably trained in 'cruel' environments that would violate their own terms of service
174