Tag
Briefings and ideas about Multimodal AI from AI podcast discussions and the research they cite, with links to the original sources.
Anekha Sokhal, Moshi's CEO and a former JPMorgan energy-derivatives trader, says her startup combines public market data with clients' private data and recommends what matters to each trader's portfolio.
Biohub's Alex Rives expects pretraining, elicitation and RLVR to carry over from language models to biology, but says verification must happen in the lab. He is unsure whether biology and language models will share one latent space.
Josh Gao, CEO of robot-data supplier Mecka AI, says labs train on about a million hours of human data, tens of thousands of gripper hours and a few teleop hours. He argues scaling that alone won't yield a robot that learns any task by watching.
Dyna Robotics chief scientist Jason Ma argues that robots should predict future camera video, not only their next moves. He says the bet could fail if touch or sound makes rival models far more data-efficient.
Tavus says 26 of 54 people who expected a one-minute video call with another human participant took its Griffin-Lite avatar for a human; they were asked about AI only after the call. On Moonshots, Richard Socher said a human-judged test can't be fully automated and warned about fake executives on Zoom.
Keerthana Gopalakrishnan, who leads Gemini Robotics research at Google DeepMind, explained how a reasoning model open to developers directs an action model limited to testers, and where she says failures arise.
Joel Borgen co-wrote his novel The Receipt Horizon with Claude and ChatGPT Pro. He says he planned the story, cut AI over-explanation and trimmed about 14%, and that good AI-assisted work still takes heavy human judgment, for now.
In one DrivingBench session, OpenAI's GPT-6 Astra drove a real Corolla through a cone course on its second try. Alexander Wissner-Gross said specialist robotics models are unnecessary; Dave Blundin questioned reliability and compute cost.
DeepSeek says V4.1-Flash's KV cache needs a quarter of the HBM and an eighth of the SSD cache of its prior generation. Moonshots panelists argued that changes what AI data centers should buy; one estimated HBM is 40% of US buildout spending.
World Labs' Atlas generates video along a user-set camera path and rebuilds scenes from photos, inventing what was not photographed. On Moonshots, Alex inferred from its documentation that it trains on Gaussian splats.
OpenAI's GPT-6 Astra nearly saturates ARC-AGI-3 and tops Epoch AI's index but ranks third by vendor family on Artificial Analysis's. Moonshots panelist Alex, lacking access, suspects it was built for fast, low-token computer use.
Peregrine's Ben Rudolph says the company's first agent reproduced detectives' findings on a closed wrongful-conviction case, and it is now used in a few US departments, including a Wisconsin county where phone records helped place a suspect.