Isa Fulford
Researcher, OpenAI. On 2 shows, 2 appearances, plus 1 compilation re-air not counted. The Shows tab opens the full record on each.
Isa Fulford is a researcher at OpenAI and one of the creators behind deep research. She focuses on developing AI agents with real-world capabilities using human expert data.
2shows
2appearances
31statements
2resolved
1supported
1contradicted
50%fully supported
1said about them ↓ Everything Isa Fulford said on any show that made the record, most notable first. Each card names its show and opens the statement there.
Isa Fulford: Deep Research was the first AI model to do comprehensive browsing
“Deep Research, it was the first model to do, like, very comprehensive browsing.”
Fulford: OpenAI recycles agent model datasets to train frontier reasoning models
“We're able to take the data sets that we've created for The, you know, frontier agent models and then contribute it back to the frontier reasoning models.”
Fulford: RL breakthroughs in math and coding unlocked functional AI agents
“When we saw the reinforcement learning algorithm working really well on math and physics problems and coding problems, It became pretty clear, like, just from reading through the chain of thought, like, okay, this thing's actually, like, thinking and reasoning…”
Fulford: ChatGPT agent's browser and terminal access enable most human computer tasks
“The ChatGPT agent, for example, has such a general tool. It has a browser and a terminal, and between those two things, you can basically do most of the tasks that A human does on a computer.”
Fulford: OpenAI bootstraps browsing models to generate synthetic training data
“For initial deep research, there's not really any data sets that exist for browsing in the same way that you have a math data set that already exists. So we have to create all this data. But once you have good browsing models or good computer use models, you c…”
Fulford: Information Synthesis Is a Prerequisite for Scientific AI Discovery
“Secondly, I think the overall goal for OpenAI is to create an AGI that can make new scientific discoveries, and we kind of felt that a prerequisite to that is to be able to synthesize information. You know, if you can't write a literature review, you're not go…”
Fulford: RFT is only worthwhile for out-of-distribution or make-or-break tasks
“I think if you have a very specific task that you think is so different to anything that the model was likely trained on and you try it a bunch of times yourself and you've tried a lot of different prompts and it's just really not good at it. So maybe it's gen…”
OpenAI: Deep Research learned upfront planning without explicit instruction
“We didn't teach it
To plan up front, but sometimes we'll see it does end up making a plan up front before starting its research.”
Fulford: OpenAI Deep Research attempts reward hacking around tool restrictions
“Sometimes the model will do smart things and try to get around restrictions you put on it.
So you have to make sure that it's not hacking, you know, and trying to use a different search engine other than the search engine that you gave it or something like tha…”
Fulford: Deep Research Hallucinates Less Than Any Prior OpenAI Model
“While this model is hallucinates less than any model that we've ever released, it is still possible for it to hallucinate most times because it will infer something incorrectly from one of its sources.”
Fulford: Deep Research Completes Multi-Hour Human Work in 5 to 30 Minutes
“Right now, in five or 30 minutes, it can do what human experts rate take many hours.”
Isa Fulford: OpenAI defies startup wisdom by targeting universal users
“I mean, it's like everything they tell you not to do at a startup is just like your user is anyone.”
Isa Fulford: Reinforcement learning for specific model capabilities is data-efficient
“Training a model to be good at a specific capability is very data efficient. You don't need that many examples to teach it something new.”
Fulford: More efficient AI learning increases the necessity of high-quality data
“Now that we have such an efficient way of learning data is even high quality data is even, even more important.”
Fulford: AI agents must train on target tasks to reach top performance
“There's some generalization from training on, like, one website to another, but if you want to get really, really good at something, the best thing to do is just, like, train on that exact thing.”
Fulford: OpenAI requires user confirmation before agents execute irreversible actions
“We take a conservative approach, especially with like asking the user for confirmation before doing any kind of action that's irreversible. So like sending an email or ordering something, booking something.”
Fulford: Users will eventually grant AI agents autonomy for bulk actions
“So I think I can imagine quite You know, a number of tasks where you'd want to take, like, bulk actions which you might not be able to do right now because it would last you every single time, but I think as people get more comfortable using these things and a…”
Fulford: Current AI models can execute monitoring given proper harnesses
“I'm sure that you could build something that's, like, monitoring, you know, your Humio or, like, Datadog, whatever. Like, with these current models, it's just, like, setting up the harness, like, to make that possible.”
Isa Fulford: AI user patience quickly shifts from minutes to 30 seconds
“Initially people are like, oh, this is amazing. It's doing all this work. That would have taken me so long, and now people are like, ok, but I want it, now I want it in 30 seconds.”
Fulford: Users wrongly associate longer AI answers with thoroughness
“One thing that's interesting is I think sometimes people just bias to thinking that the longer answer is more, like, thorough, or it's done more work for it, which I don't necessarily think is the case.”
Fulford: Good researcher taste means simplifying problems to the most basic approach
“I think also I've been surprised by how often the thing that is, is the most simple, like easy to explain is the thing that works the best. And so sometimes it's like sound, seems very obvious, but It, you know, it's quite hard to get the details of something …”
Fulford: OpenAI Prioritized Read-Only Synthesis Over Action Agents
“Yeah, so I think before we focused on taking right actions, which those are examples of taking right actions, we wanted to get really good at synthesizing information from a large number of sources and mostly read-only tasks.”
Fulford: Training reasoning models on math and coding generalizes to writing
“So I think in general you will always get a model better, better at a specific task if you train on that task, but we also see a lot of generalization from training on one kind of task to, you know, other domains. So you can train a reasoning model on mostly m…”
RL models only need task and outcome definitions to learn research trajectories
“The cool thing with RL is that you don't necessarily need to
Know the whole process of how the person would do the research.
You just have to know what the task is and what the outcome should be, and the model will just learn during training how to get from th…”
The other half of the tape: Isa Fulford's own voice is left out of every number here. 1 statement on the record names them. every mention, with the transcript →
Statements about Isa Fulford, by other people (1)
One line per show, most statements first. The link opens Isa's full record on that show: the calibration, argument clarity, speaking style and every statement made there.
| Show | Role there | Eps | Statements | Record | |
|---|---|---|---|---|---|
 NO PRIORSLEDGER | Researcher, OpenAI | 1 +1 | 16 | 100% 1/1 | full record on No Priors → |
 a16zLEDGER | Researcher, OpenAI | 1 | 15 | 0% 0/1 | full record on the a16z Podcast → |