World Model · podcast knowledge graph

The Agent Reasoning Interface: o1/o3, Claude 3, ChatGPT Canvas, Tasks, and Operator — with Karina Nguyen of OpenAI

2025-02-01 · 69 min · 18 entities

episode page audio

Asserted relationships

  • → appeared on Latent Space: The AI Engineer Podcast podcast
    0.68
    evidence rules-v4
    The Agent Reasoning Interface: o1/o3, Claude 3, ChatGPT Canvas, Tasks, and Operator — with Karina Nguyen of OpenAI
  • → works at Decibel company
    0.50
    evidence rules-v4
    CTO at Decibel
  • → works at Decibel company
    0.50
    evidence rules-v4
    CTO at Decibel
  • → works at Anthropic company
    0.48
    evidence rules-v4
    joined Anthropic
  • → works at Anthropic company
    0.48
    evidence rules-v4
    joined Anthropic
  • → discusses Science concept
    0.40
    evidence rules-v4
    Feed category: Science
  • → discusses Technology concept
    0.40
    evidence rules-v4
    Feed category: Technology
  • → references Introducing Canvas person
    0.38
    evidence rules-v4
    Link in episode "The Agent Reasoning Interface: o1/o3, Claude 3, ChatGPT Canvas, Tasks, and Operator — with Karina Nguyen of OpenAI": https://openai.com/index/introducing-canvas
  • 0.38
    evidence rules-v4
    Link in episode "The Agent Reasoning Interface: o1/o3, Claude 3, ChatGPT Canvas, Tasks, and Operator — with Karina Nguyen of OpenAI": https://theverge.com/2025/1/14/24343528/openai-chatgpt-repeating-tasks-agent-ai
  • → references Introducing Operator person
    0.38
    evidence rules-v4
    Link in episode "The Agent Reasoning Interface: o1/o3, Claude 3, ChatGPT Canvas, Tasks, and Operator — with Karina Nguyen of OpenAI": https://openai.com/index/introducing-operator

Entities found in this episode

companys 6

  • mentioned Decibel company
    0.62
    evidence rules-v4
    CTO at Decibel
  • mentioned Anthropic company
    0.60
    evidence rules-v4
    joined Anthropic
  • works at Decibel company
    0.50
    evidence rules-v4
    CTO at Decibel
  • works at Decibel company
    0.50
    evidence rules-v4
    CTO at Decibel
  • works at Anthropic company
    0.48
    evidence rules-v4
    joined Anthropic
  • works at Anthropic company
    0.48
    evidence rules-v4
    joined Anthropic

persons 5

  • mentioned Karina Nguyen of Op person
    0.72
    evidence rules-v4
    The Agent Reasoning Interface: o1/o3, Claude 3, ChatGPT Canvas, Tasks, and Operator — with Karina Nguyen of OpenAI
  • mentioned Introducing Canvas person
    0.45
    evidence rules-v4
    Link in episode "The Agent Reasoning Interface: o1/o3, Claude 3, ChatGPT Canvas, Tasks, and Operator — with Karina Nguyen of OpenAI": https://openai.com/index/introducing-canvas
  • mentioned Introducing Operator person
    0.45
    evidence rules-v4
    Link in episode "The Agent Reasoning Interface: o1/o3, Claude 3, ChatGPT Canvas, Tasks, and Operator — with Karina Nguyen of OpenAI": https://openai.com/index/introducing-operator
  • references Introducing Canvas person
    0.38
    evidence rules-v4
    Link in episode "The Agent Reasoning Interface: o1/o3, Claude 3, ChatGPT Canvas, Tasks, and Operator — with Karina Nguyen of OpenAI": https://openai.com/index/introducing-canvas
  • references Introducing Operator person
    0.38
    evidence rules-v4
    Link in episode "The Agent Reasoning Interface: o1/o3, Claude 3, ChatGPT Canvas, Tasks, and Operator — with Karina Nguyen of OpenAI": https://openai.com/index/introducing-operator

concepts 4

  • mentioned Science concept
    0.50
    evidence rules-v4
    Feed category: Science
  • mentioned Technology concept
    0.50
    evidence rules-v4
    Feed category: Technology
  • discusses Science concept
    0.40
    evidence rules-v4
    Feed category: Science
  • discusses Technology concept
    0.40
    evidence rules-v4
    Feed category: Technology

websites 2

  • 0.45
    evidence rules-v4
    Link in episode "The Agent Reasoning Interface: o1/o3, Claude 3, ChatGPT Canvas, Tasks, and Operator — with Karina Nguyen of OpenAI": https://theverge.com/2025/1/14/24343528/openai-chatgpt-repeating-tasks-agent-ai
  • 0.38
    evidence rules-v4
    Link in episode "The Agent Reasoning Interface: o1/o3, Claude 3, ChatGPT Canvas, Tasks, and Operator — with Karina Nguyen of OpenAI": https://theverge.com/2025/1/14/24343528/openai-chatgpt-repeating-tasks-agent-ai

podcasts 1

  • 0.68
    evidence rules-v4
    The Agent Reasoning Interface: o1/o3, Claude 3, ChatGPT Canvas, Tasks, and Operator — with Karina Nguyen of OpenAI
Episode description as stored
Sponsorships and tickets for the AI Engineer Summit are selling fast ! See the new website with speakers and schedules live! If you are building AI agents or leading teams of AI Engineers , this will be the single highest-signal conference of the year for you, this Feb 20-22nd in NYC. We’re pleased to share that Karina will be presenting OpenAI’s closing keynote at the AI Engineer Summit. We were fortunate to get some time with her today to introduce some of her work, and hope this serves as nice background for her talk! There are very few early AI careers that have been as impactful as Karina Nguyen’s. After stints at Notion, Square, Dropbox, Primer, the New York Times, and UC Berkeley, She joined Anthropic as employee ~60 and worked on a wide range of research/product roles for Claude 1, 2, and 3. We’ll just let her LinkedIn speak for itself: Now, as Research manager and Post-training lead in Model Behavior at OpenAI, she creates new interaction paradigms for reasoning interfaces and capabilities, like ChatGPT Canvas , Tasks , SimpleQA , streaming chain-of-thought for o1 models , and more via novel synthetic model training. Ideal AI Research+Product Process In the podcast we got a sense of what Karina has found works for her and her team to be as productive as they have been: * Write PRD (Define what you want) * Funding (Get resources) * Prototype Prompted Baseline (See what’s possible) * Write and Run Evals (Get failures to hillclimb) * Model training (Exceed baseline without overfitting) * Bugbash (Find bugs and solve them) * Ship (Get users!) We could turn this into a snazzy viral graphic but really this is all it is. Simple to say, difficult to do well. Hopefully it helps you define your process if you do similar product-research work. Show Notes * Our Reasoning Price War post * Karina LinkedIn , Website , Twitter * OSINT visualization work * Ukraine 3D storytelling * Karina on Claude Artifacts * Karina on Claude 3 Benchmarks * Inspiration for Artifacts / Canvas from early UX work she did on GPT-3 * “ i really believe that things like canvas and tasks should and could have happened like 2 yrs ago, idk why we are lagging in the form factors” ( tweet ) * Our article on prompting o1 vs Karina’s Claude prompting principles * Canvas : https://openai.com/index/introducing-canvas/ * We trained GPT-4o to collaborate as a creative partner. The model knows when to open a canvas, make targeted edits, and fully rewrite. It also understands broader context to provide precise feedback and suggestions. To support this, our research team developed the following core behaviors: * Triggering the canvas for writing and coding * Generating diverse content types * Making targeted edits * Rewriting documents * Providing inline critique We measured progress with over 20 automated internal evaluations. We used novel synthetic data generation techniques, such as distilling outputs from OpenAI o1-preview, to post-train the model for its core behaviors. This approach allowed us to rapidly address writing quality and new user interactions, all without relying on human-generated data. * Tasks: https://www.theverge.com/2025/1/14/24343528/openai-chatgpt-repeating-tasks-agent-ai * * Agents and Operator * What are agents? “ Agents are a gradual progression of tasks: starting with one-off actions, moving to collaboration, and ultimately fully trustworthy long-horizon delegation in complex envs like multi-player/multiagents.” ( tweet ) * tasks and canvas fall within the first two, and we are def. marching towards the third—though the form factor for 3 will take time to develop * Operator/Computer Use Agents * https://openai.com/index/introducing-operator/ * Misc: * Andrew Ng * Prediction: Personal AI Consumer playbook * ChatGPT as generative OS Timestamps * 00:00 Welcome to the Latent Space Podcast * 00:11 Introducing Karina Nguyen * 02:21 Karina's Journey to OpenAI * 04:45 Early Prototypes and Projects * 05:25 Joining Anthropic and Early Work * 07:1