By playing, you agree to uListen's Terms and Privacy Policy and YouTube's Terms of Service.
Latent SpaceGPT 4.1: The New OpenAI Workhorse
Summaries, chapters, transcripts, and FAQs on this page are made by uListen, not YouTube.
Episode Details
EPISODE INFO
- Released
- April 15, 2025
- Duration
- 45m
- Channel
- Latent Space
- Watch on YouTube
- ▶ Open ↗
EPISODE DESCRIPTION
We’ll keep this brief because we’re on a tight turnaround: GPT 4.1, previously known as the Quasar and Optimus models, is now live as the natural update for 4o/4o-mini (and the research preview of GPT 4.5). Though it is a general purpose model family, the headline features are: Coding abilities (o1-level SWEBench and SWELancer, but ok Aider) Instruction Following (with a very notable prompting guide) Long Context up to 1m tokens (with new MRCR and Graphwalk benchmarks) Vision (simply o1 level) Cheaper Pricing (cheaper than 4o, greatly improved prompt caching savings) We caught up with returning guest Michelle Pokrass and Josh McGrath to get more detail on each! Part 1 00:00:00 Introduction and Guest Welcome 00:00:57 GPT 4.1 Launch Overview 00:01:54 Developer Feedback and Model Names 00:02:53 Model Naming and Starry Themes 00:03:49 Confusion Over GPT 4.1 vs 4.5 00:04:47 Distillation and Model Improvements 00:05:45 Omnimodel Architecture and Future Plans 00:06:43 Core Capabilities of GPT 4.1 00:07:40 Training Techniques and Long Context 00:08:37 Challenges in Long Context Reasoning 00:09:34 Context Utilization in Models Part 2 00:10:31 Graph Walks and Model Evaluation 00:11:31 Real Life Applications of Graph Tasks 00:12:30 Multi-Hop Reasoning Benchmarks 00:13:30 Agentic Workflows and Backtracking 00:14:28 Graph Traversals for Agent Planning 00:15:24 Context Usage in API and Memory Systems 00:16:21 Model Performance in Long Context Tasks 00:17:17 Instruction Following and Real World Data 00:18:12 Challenges in Grading Instructions 00:19:09 Instruction Following Techniques 00:20:09 Prompting Techniques and Model Responses 00:21:05 Agentic Workflows and Model Persistence Part 3 00:22:01 Balancing Persistence and User Control 00:22:56 Evaluations on Model Edits and Persistence 00:23:55 XML vs JSON in Prompting 00:24:50 Instruction Placement in Context 00:25:49 Optimizing for Prompt Caching 00:26:49 Chain of Thought and Reasoning Models 00:27:46 Choosing the Right Model for Your Task 00:28:46 Coding Capabilities of GPT 4.1 00:29:41 Model Performance in Coding Tasks 00:30:39 Understanding Coding Model Differences 00:31:36 Using Smaller Models for Coding 00:32:33 Future of Coding in OpenAI Part 4 00:33:28 Internal Use and Success Stories 00:34:26 Vision and Multi-Modal Capabilities 00:35:25 Screen vs Embodied Vision 00:36:22 Vision Benchmarks and Model Improvements 00:37:19 Model Deprecation and GPU Usage 00:38:13 Fine-Tuning and Preference Steering 00:39:12 Upcoming Reasoning Models 00:40:10 Creative Writing and Model Humor 00:41:07 Feedback and Developer Community 00:42:03 Pricing and Blended Model Costs 00:44:02 Conclusion and Wrap-Up
SPEAKERS
Alessio Fanelli
hostPartner and CTO at Decibel and co-host of the Latent Space podcast.
swyx
hostFounder of Smol.ai and co-host of the Latent Space podcast.
Michelle Pokrass
guestOpenAI research lead in post-training (previously associated with the API team).
Josh McGrath
guestOpenAI post-training researcher on Michelle Pokrass’s team, focused on long-context work.
EPISODE SUMMARY
In this episode of Latent Space, featuring Alessio Fanelli and swyx, GPT 4.1: The New OpenAI Workhorse explores GPT 4.1: developer-focused models with stronger coding and million context OpenAI released GPT 4.1, 4.1 Mini, and 4.1 Nano, with the guests emphasizing developer-centric improvements in instruction following, coding, and a one-million-token context window.
RELATED EPISODES
