# Verification speed sets the limits for AI research agents

Markdown copy of https://realalpha.app/s/verification-speed-sets-the-limits-for-ai-research-agents/ on Real Alpha, the best minutes from long interviews with the people building AI. Cite and link the page, not this copy.

- Speaker: [Richard Socher](https://realalpha.app/builders/richard-socher/) · Richard Socher is a former chief scientist at Salesforce, founder of You.com and cofounder of Recursive. · Pioneered neural networks in NLP, invented widely used word and contextual vectors, and leads Recursive's self-improving AI.
- Host: [Sam Charrington](https://realalpha.app/people/sam-charrington/) · Host, The TWIML AI Podcast
- Show: The TWIML AI Podcast
- Episode: [Can AI Invent or Just Help Scientists Work Faster?](https://realalpha.app/v/rIUcQfyXuUo/), Nov 3, 2026
- Moment: 32:59 to 37:49 of the episode (5 min), playing on https://realalpha.app/s/verification-speed-sets-the-limits-for-ai-research-agents/; the episode from there: https://realalpha.app/v/rIUcQfyXuUo/?t=1979

## Quote

> “even if you can have a verifier but the verifier **takes like a year to run** not that useful right”
> — [Richard Socher](https://realalpha.app/builders/richard-socher/) at [35:44](https://realalpha.app/v/rIUcQfyXuUo/?t=2144) · The TWIML AI Podcast

## Takeaways

1. Short verification loops make agent experiments easier to improve.
2. Long-running tests make results harder to evaluate and attribute.
3. The same underlying system can work across different tools and tasks.

## About this segment

Richard Socher says faster verification makes it easier to improve agent-driven research; a year-long check is barely useful. Long experiments also make it harder to credit intermediate decisions.

From “Can AI Invent or Just Help Scientists Work Faster?”, Nov 3, 2026. [Watch the full episode](https://realalpha.app/v/rIUcQfyXuUo/)

## Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

[33:02](https://realalpha.app/v/rIUcQfyXuUo/?t=1982) How do you describe what the technology is at its core? I don't want to give away too much, but, you know, one way to describe it is like, it's like as if you had 20,000 AI researchers doing AI research for you and optimizing whatever you care about in a very short amount of time. The approximation is like, yeah, it is like a somewhat of a community of AI scientists, essentially. One part of that is, you know, this thing you care about and some way of translating that into some objective that can be shared by a bunch of agents that your thing spins up and somehow parses work out to and, you know, evaluates that work, etc.

[33:46](https://realalpha.app/v/rIUcQfyXuUo/?t=2026) do you have a sense at this point for like what the constraints are in the sense of like what recursive is going to be good at versus what it's not going to be good at i mean one thing is clear that like this this kind of approach uh the faster you can verify something the easier it is for everyone um like and and you've seen that uh in in the simpler examples of nano chat uh already like a lot of people made some progress um and you know we can make even more progress um i think the longer it takes to verify whether a result is good the more clever you have to be and the less i can talk about how we how we do it um and that's why we haven't like published all our results yet but like that's kind of um those results are easier to to verify quickly and then we're going to release some things about a month from now

[34:42](https://realalpha.app/v/rIUcQfyXuUo/?t=2082) that people will see like, okay, that was definitely not a five-minute type of situation to get a result for. And even there, it starts to make progress. What I heard in this verifiability, I also heard kind of traditional attribution problems and that kind of thing. Are you saying both of those things or are you saying more of the attribution type of an issue? On the one hand, you have like, you know, the idea of verifiable rewards, like, you know, this is a task that, you know, the agent can clearly and easily distinguish whether it got it right or wrong and then you can kind of get that loop going.

[35:21](https://realalpha.app/v/rIUcQfyXuUo/?t=2121) You know, on the other side, you've got, you know, the task involves long sequences of things and the agent can make decisions in the middle and not really know whether those decisions are right or wrong until the end. you know is it kind of all of the above is you know where the challenges are and you've got something in mind that addresses all of that or is it one or the other of those that you've kind of figured out it's it's all of the above yeah like all of these need to be all of these are important even if you can have a verifier but the verifier takes like a year to run not that useful right like or and then and then there's like an interpolation of how useful it is right if you get it down to like a minute, extremely useful.

[36:00](https://realalpha.app/v/rIUcQfyXuUo/?t=2160) and if it takes a year and it's almost used less completely and so then you need to be clever about dealing with that part if you yeah so that's an aspect now some cases you have indeed multiple steps and then you have just sort of the attribution of each step and how important it was and how do you deal with that there's a lot of different pieces that need to be figured out and in some cases there are research papers that we've published um uh four of the five authors of the darwin girdle machine paper for instance uh from from jeff bluen who's the most senior author on that paper and jenny is the first author um they're both with us and like you know that is an example of of what you can do um also uh that um yeah is a little bit more complex uh but already shows you kind of the sign of things to come. How do you think about kind of the generalizability of what you

[36:59](https://realalpha.app/v/rIUcQfyXuUo/?t=2219) have today? You know, meaning, you know, even for these, the three examples you talked about, like, were they three largely disparate efforts or was it mostly the same kind of effort applied, lightly applied to three different areas? Does that question make sense? Yeah. I mean, there's like, you know, sometimes it's useful to have an extra tool, for instance, in kernels, you can have like a kernel profiler and that's a very useful tool to just understand a little bit more inside this sort of black box what's happening and what's going on. But outside of that, it's basically all just like different tool use and it's the same underlying Eureka machine, which is kind of cool.

[37:39](https://realalpha.app/v/rIUcQfyXuUo/?t=2259) That's what gives us hope. That and a few other things I can't talk about yet and results that we're seeing that gives us hope that there's something here and it's time to scale it up more.