CLIP
includes CLIP ViT L
2 statements across 2 episodes · 1 bullish · 1 bearish · 2 people on the record · first statement Dec 22, 2024 by Peter Robicheaux · said 49 times in 15 episodes since 2023 · across every show →
Mentions by year, the whole family
brought up most by Vibhu Sapra (13), Peter Robicheaux (11), comfyanonymous (Comfy) (6), Ben Firshman (2), Alessio Fanelli (2), Varun Mohan (1), Shawn Wang (1), Ludwig Schmidt (1)
tap a year for its mentions
2026 3 mentions in 2 episodes 2 per episode
2025 11 mentions in 4 episodes 3 per episode
- AI Engineering for Art - with comfyanonymous
- Terminal-Bench 2.0: the most impt coding agent benchmark of 2025 gets a v2! Launch + Q&A w/ founders
- 🕰️ The Oral History of Windsurf (ft. Varun Mohan, Scott Wu, Jeff Wang, Kevin Hou, Anshul R)
- The Agent Reasoning Interface: Claude, ChatGPT Canvas, Tasks, Operator — with Karina Nguyen, OpenAI
- every mention in 2025, scene by scene →
2024 33 mentions in 7 episodes 5 per episode
- [Paper Club] Molmo + Pixmo + Whisper 3 Turbo - with Vibhu Sapra, Nathan Lambert, Amgadoz
- Best of 2024 in Vision [LS Live @ NeurIPS]
- [Paper Club] Embeddings in 2024: OpenAI, Nomic Embed, Jina Embed, cde-small-v1 - with swyx
- A Brief History of the Open Source AI Hacker - with Ben Firshman of Replicate
- [Paper Club] Berkeley Function Calling Paper Club! — Sam Julien, Writer
- High Agency Pydantic over VC Backed Frameworks — with Jason Liu of Instructor
- The Origin and Future of RLHF: the secret ingredient for ChatGPT - with Nathan Lambert
- every mention in 2024, scene by scene →
2023 2 mentions in 2 episodes 1 per episode
Everything said about CLIP, oldest first
Dec 22, 2024 negative
Robicheaux: CLIP encoders lack fine-grained visual features due to caption-matching objective
“Models that have been initialized with Clip as their vision encoder, they don't have fine-grained details and the features extracted using Clip because Clip sort of doesn't need to find these fine grade details to do its job correctly, which is just to match c…”
Jul 28, 2025 positive
Mohan: Enterprises should fine-tune off-the-shelf models over custom architectures
“For a vast majority of enterprises, they should probably be using something off the shelf, fine tuning BERT models. If it's a vision, they should be fine tuning resonant or using something like clip, like the less work they can do the better.”