Latent Space / episode intelligence
Speakers in the public record
Claim mix
Evidence policy
Every row below preserves an exact excerpt. Identified speakers are linked; unresolved voices are labeled and excluded from people counts.
Claim ledger
38 published records
01 / recommendation
“On that note, I think OpenAI even recommended when you're doing tool calling, it's sometimes helpful to put a thought field in the tool, along with all the actual acquired arguments,”
02 / belief
“Oh, so there's that one. And then there's like the celebrity one by the same author, I think.”
03 / belief
“I think the Cognitive Architecture for Language Agents paper has a good categorization of all the different combinations.”
04 / belief
“I think another interesting thing is like, I personally have never done those kind of like weird tricks.”
05 / belief
“Summarization has a track, question answering has a track. So I think really it's about rethinking agents in terms of what could be the new environments that we came to have is not just Atari games or whatever video games, but also those text games or language games.”
06 / belief
“There's a few data sets kind of like in that vein that require multi-step kind of like reasoning and thinking. So one of the questions I actually had for you in this vein, like the React paper, there's a few things in there, or at least when I think of that, there's a few things that I think of.”
07 / belief
“We haven't thought about that from the perspective, like we're not trying to design LangChain or LangGraph to be friendly. But I mean, I think to be friendly for agents to write.”
08 / belief
“I think that's actually the last paragraph of the paper that's talking about this.”
09 / belief
“I think making the tool good and reliable is probably like 90% of the whole agent.”
10 / belief
“I think the practical reason it has become less used is because the agent kind of scaffold become more complex or the task you're trying to solve is becoming more complex.”
11 / belief
“I think that to me is maybe one of the bigger unsolved things in terms of agents is just memory.”
12 / belief
“I think the contribution of React is just to point out that we can also have internal actions called thinking.”
13 / belief
“If we think about a lot of the stuff we do, I'm just thinking out loud now, but a lot of the stuff we do on agents now is through Langraff.”
14 / belief
“What do you think about the role of few-shot prompting for some of these like agent trajectories? That was a big part of the original React paper, I think.”
15 / belief
“I mean, I have a blog that I published at some point on this. But I think like right off the bat, there's like procedural memory, which is like how you do things.”
16 / belief
“I think the first demo we did probably had like a calculator tool and a search tool.”
17 / belief
“I think the whole thesis of symbolic AI is, we should just be able to write down all the knowledge, and that just creates intelligence, but that kind of fails.”
18 / belief
“We do this kind of iterative fixing. But I think what's really interesting is there'll be a lot of future directions that's very promising if we can apply some of the HCI principles more systematically into the interface design.”
19 / belief
“Like you write down literally everything you think about and everything you do on the computer and you record them and you train on all the successful trajectories by some metric of success. I think that should just lead us to AGI.”
20 / belief
“I think right now it's a good opportunity to, if you really just care about this task of customer service, then it's a good opportunity because now you have LLMs to simulate humans.”
21 / belief
“I think that was our most popular webinar we did on LinkedIn. I think Harrison promoted the paper a lot, thanks to him.”
22 / belief
“Then I think, even in that point, I think something like Koala is still useful if we want to do some neuroscience on GPT-10.”
23 / belief
“I think one way to think of reflection is that the traditional idea of reinforcement learning is you have a scalar reward and then you somehow back-propagate the signal of the scalar reward to the rest of your neural network through whatever algorithm, like policy grading or A2C or whatever.”
24 / belief
“I think like when you talk about designing tools, it's not only the, it's the interface in the entirety, not only the inputs, but also the outputs that really matter.”
25 / belief
“If you're using a knowledge graph as a hammer to hit a nail, it's not that. But I think practically what we see is it's still so application specific what relevant memory is.”
26 / belief
“For example, if you're finding a math proof or if you're finding a good code to solve a problem or whatever, I think another type of task is more like reacting.”
27 / belief
“I think that's a very interesting point. You're trying to optimize to the extreme, then obviously they're going to be different.”
28 / belief
“You know, it's like. It may be, but I also think I would say on average, people are probably worse at communicating with language models than to humans right now, at least, because I think we're still figuring out how to do it.”
29 / evaluation
“I'm pretty science-based, like, you know, but probably the most like spiritual woo-woo thing about me is I don't think that would lead to consciousness or AGI just because like there's something in- there's a soul, you know?”
30 / preference
“Yeah, I'm a big fan of Simulative AI. We had a summer of Simulative AI. Another term we're trying to coin.”
31 / prediction
“Actually, Singapore is the first country to build the cyber range for cyber attack training. And I think you'll see more of that.”
32 / prediction
“I think that's the main learning I have from Devin. They cracked that. Actually, there was no foundational planning breakthrough.”
33 / recommendation
“The way I put this is you should not be a prompt engineer because it is the goal of the big labs to put you out of a job.”
34 / evaluation
“I think OpenAI was just like, look, this is a thing now. We have to fix this. These students just rushed it.”
35 / evaluation
“You're one of like, you're maybe the first PhD thesis defense I've ever watched in like this AI world, because most people just publish single papers, but every paper of yours is a banger.”
36 / prediction
“I actually always wanted to take like a selfie and go like, you know, POV, you're about to revolutionize the world of agents because we have two of the most awesome hiring agents in the house.”
37 / evaluation
“I will mostly agree and I'll slightly disagree in terms of this, which is like, whether designing for humans also overlaps with designing for AI. So Malte Ubo, who's the CTO of Vercel, who is creating basically JavaScript's competitor to LangChain, they're observing that basically, like if the API is easy to understand for humans, it's actually much easier to understand for LLMs, for example, because they're not overloaded functions.”
38 / evaluation
“Like, I actually have most of my problems with AI news when the model thinks it knows more than it knows because it combines knowledge with intelligence.”