GPT-OSS, every mention
13 scenes · ← back to GPT-OSS
tap a year for its mentions
every year anyone Shawn Wang 2Sean Lie 2Ronak Malde 2Micah Hill-Smith 1Kyle Kranen 1Elie Bakouch 1Barak Lenz 1
Verbatim, from the transcripts: the passages where GPT-OSS comes up
The Inference Frontier: from 100 to 10,000 tokens per second — Sean Lie, Cerebras CTO
- ▶ 5:16 Sean Lie We here in this, in this demo that we gave, uh, at hot chips, um, we're showing, uh, GPT OSS, uh, running at over 4000, uh, 400 TPS, which is just mind blowing.
- ▶ 11:25 Sean Lie And what this ultimately means is you'll be able to run, you know, medium sized models like GPT-OSS or JAMA at speeds up to 10,000 TPS.
⚡️Every product of the future will be a living system — Ronak Malde, Trajectory.ai
- ▶ 14:57 Ronak Malde You can already see, like, um, I mean, GPT-OSS was kind of one of the best base models a year ago that OpenAI put out, uh, in the Western world. 2 times in the scene
AI-Native Engineering: 100% adoption, 5x search throughput, unlimited tokens — Mikhail Parakhin
- ▶ 45:10 Shawn Wang Yeah, so you're running, uh, GPT-OSS. 2 times in the scene
Agent Inference at the "Speed of Light" — How NVIDIA moves like a $4.3 Trillion Startup
- ▶ 45:20 Kyle Kranen We see models like Kimi or GPT-OSS.
Captaining IMO Gold, Deep Think, On-Policy RL, Feeling the AGI in Singapore — Yi Tay
- ▶ 53:25 unnamed speaker Would you say that the ideas that I see there, Nvidia has NemoTron, OpenAI has GPT-OSS, these are all basically checkpoints on what's publicly known about training models as of this year.
Artificial Analysis: The Independent LLM Analysis House — with George Cameron and Micah Hill-Smith
- ▶ 1:04:44 Micah Hill-Smith So the GPD OSS models, like the big ones at about five percent, um, active.
How Zyphra went all-in on AMD + Why Devs feel faster with AI but are slower — with Quentin Anthony
- ▶ 23:58 unnamed speaker The GPT-Five to GPT-OSS handoff, for example, that could happen, where you have OSS on the device, and then it hands off to GPT-Five for more compute-intensive tasks. 3 times in the scene
⚡ Open Model Pretraining Masterclass — Elie Bakouch, HuggingFace SmolLM 3, FineWeb, FinePDF
- ▶ 28:40 Elie Bakouch A GPT OSS coin three doesn't have Shard Expert, but like the coin three next, which is like, uh, really is like, uh, I mean, they didn't release it yet, but they submit the PR to Transformers.
Building Jamba 3B: the tiny Hybrid Transformer State Space Reasoning Model - Barak Lenz, CTO of AI21
- ▶ 40:36 Barak Lenz Even if I want to use GPT-OSS, I've taken in a lot of different policies about what to abstain from, what's considered dangerous and not dangerous, how I should behave, etc.
Greg Brockman on OpenAI's Road to AGI
- ▶ 0:22 unnamed speaker Congrats on GPT-Five, GPT-OSS, like all the stuff that's going on in OpenAI Lands. 2 times in the scene
- ▶ 39:26 unnamed speaker One thing I wanted to touch on for the, I think the last kind of last couple of topics on GPT five, before we move to OSS, you've acknowledged that there's a router, which is really cool.
- ▶ 47:41 unnamed speaker Sliding window attention, the very fine-grained mixture of experts, which I think DeepSeek popularized, rope, yarn, attention sinks, any, anything that, you know, I think stood out to you and, uh, the choices made for GPT-OSS? 2 times in the scene