GPT-4o mini, every mention

25 scenes · ← back to GPT-4o mini

tap a year for its mentions
00138251520242025episodesmentions
081520242025episodes it came up in
001.57.531520242025episodesmentions per episode

every year anyone Shawn Wang 7Michelle Pokrass 7Pratik Bhavsar 4Thomas Paul Mann 3Elie Bakouch 3Shreya Shankar 2Bret Taylor 1Ankur Goyal 1Alistair Pullen 1Alex Duffy 1

Verbatim, from the transcripts: the passages where GPT-4o mini comes up

loading…

⚡ Open Model Pretraining Masterclass — Elie Bakouch, HuggingFace SmolLM 3, FineWeb, FinePDF Oct 20, 2025 · 3 mentions

  • ▶ 32:04 Elie Bakouch I will just not allocate, and I will basically do inference with fewer experts, which is the equivalent of GPT-V mini, for example. 2 times in the scene
  • ▶ 39:11 Elie Bakouch And that's like the same logic for, uh, the, the, the model router, basically, because you, you are selecting the model with, like, fewer activated flops for, you know, the GPT-V mini compared to the big one.

⚡️Ranking Agentic LLMs — Pratik Bhavsar, Galileo Jul 14, 2025 · 4 mentions

⚡️Launching AI Diplomacy: the hardest LLM Game Benchmark yet - Alex Duffy Jun 11, 2025 · 1 mention

  • ▶ 16:19 Alex Duffy I think one of the things that we'll do next is have three O four minis versus cloud two five pros and allow them to, you know, create an alliance, essentially like, you know, change their system prompts so that they, they know if any of…

⚡️Factorio Learning Environment: the ultimate Game Agent Eval — Jack Hopkins Apr 27, 2025 · 1 mention

  • ▶ 16:51 unnamed speaker Yeah, yeah, I think GBT-IV had a, and it's the same with Mini as well, if I remember correctly.

Sleep-Time Compute — Letta AI (Charles Packer, Charlie Snell, Kevin Lin) Apr 21, 2025 · 1 mention

  • ▶ 23:10 Alessio Fanelli Yeah, I'm curious because you have for a mini and you have for all, I'm curious, like, if you think that makes a big difference or not as much.

GPT 4.1: The New OpenAI Workhorse Apr 15, 2025 · 2 mentions

  • ▶ 4:55 unnamed speaker And then the many is strictly better than four or many.
  • ▶ 32:15 Michelle Pokrass Um, so you can see, like, 4.1 mini is actually quite significantly better than four o mini, um, and not that far away from the old four o.

Raycast: Your AI Automation Assistant Feb 26, 2025 · 3 mentions

  • ▶ 8:15 Thomas Paul Mann and so we looked into all the various models we had, um, and then we picked, at the moment, it's gbd-for-o and gbd-for-o-mini, 3 times in the scene

The AI Architect: Bret Taylor Feb 11, 2025 · 1 mention

  • ▶ 1:33:13 Bret Taylor Once you got to four O and four O mini, you know, it, it opened the door to a lot of different applications, both for cost and latency.

Why every AI Engineer needs an AI Gateway (ft Portkey.ai CEO) Feb 5, 2025 · 1 mention

  • ▶ 2:25 unnamed speaker I think before maybe there wasn't as much value of like routing between four or like four or many, you kind of knew what to use, but now the latency of the reasoning model is much higher.

The Unreasonable Effectiveness of Reasoning Distillation: using DeepSeek R1 to beat OpenAI o1 Jan 24, 2025 · 1 mention

  • ▶ 17:38 unnamed speaker Using GPT for Omidy.

2024 Year in Review: The Big Scaling Debate, the Four Wars of AI, Top Themes and the Rise of Agents Jan 1, 2025 · 2 mentions

  • ▶ 1:17:43 Shawn Wang Um, and I think what you're starting to see now, uh, in July is the emergence of four O mini and deep sea V two as outliers to the July frontier where July frontier used to be maintained by four O Lama four five. 2 times in the scene

[Paper Club] DocETL: Agentic Query Rewriting + Eval for Complex Document Processing w Shreya Shankar Nov 29, 2024 · 2 mentions

  • ▶ 45:58 Shreya Shankar The reason it was a hundred dollars, if, if I ran the optimizer with GPT-Foro mini as the LLMs, it would be 10 dollars. 2 times in the scene

Production AI Engineering starts with Evals Oct 11, 2024 · 1 mention

  • ▶ 1:25:04 Ankur Goyal Post-Claude III, uh, and I actually think Haiku is, is slept on a little bit, because before Foro Mini came out, Haiku was a very interesting reprieve, uh, for people to have very, very cheap.

Building AGI in Real Time (OpenAI Dev Day 2024) Oct 4, 2024 · 1 mention

  • ▶ 48:14 Shawn Wang Yeah, I sat in the distillation session just now, and they showed how they distilled from four to four mini, and, uh, it was like only like a two percent hit in the performance, and 15 X cheaper.

The Ultimate Guide to Prompting - with Sander Schulhoff from LearnPrompting.org Sep 20, 2024 · 2 mentions

Building AGI with OpenAI's Structured Outputs API Sep 17, 2024 · 8 mentions

  • ▶ 30:14 Shawn Wang Able to apply the structured output system on backdated models, like, uh, for May, as well as mini, as well as August. 2 times in the scene
  • ▶ 40:56 Michelle Pokrass In general, I think folks should start with Foro Mini. 4 times in the scene
  • ▶ 58:34 Michelle Pokrass It also works with, like, Foro Mini, so the savings on top of Foro Mini is pretty crazy, like the stuff you can do. 2 times in the scene

Is finetuning GPT4o worth it? Aug 22, 2024 · 1 mention

The Winds of AI Winter (Q2 Four Wars of the AI Stack Recap) Aug 2, 2024 · 3 mentions

  • ▶ 5:03 unnamed speaker Benchmarks on LMSYS or coding benchmarks on LMSYS, it is the undisputed number one model in the world, even with Foro Mini. 2 times in the scene
  • ▶ 42:59 unnamed speaker and then distilled it down to four O mini.

[LLM Paper Club] Llama 3.1 Paper: The Llama Family of Models Jul 29, 2024 · 3 mentions

  • ▶ 13:39 unnamed speaker So he started fine-tuning it, um, compared it to Foro Mini. 3 times in the scene
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.