agent

“Agents haven't been productized yet for, partly for this reason, is that, like, the abstractions are very leaky. You know, we can get, like, 80% of the way there, but, like, self-driving cars, like, the remaining 20% is actually really difficult.”

“So we think sort of the AI workflow space is a really exciting space, and I think that is the next step in sort of delivering a lot of business value by AI. I personally don't think it's, you know, via chat or, you know, via agents quite yet, so.”

“In a world where foundation models are looking more and more commodity. And if, and I think a huge amount of gain is going to happen from how do you use foundation models as like the, like well learned behavioral cloner to go solve agents.”

“I expect some incremental and significant progress on pre-training and post-training, but I'm really hopeful that we can gain some order of magnitude of scaling by interconnecting well models into agents as a more complex system that can do planning, that can …”

“Like if something is 95% reliable, but you're chaining together a bunch of calls, if you magnify that error rate, it makes your like application not work. So that's a really exciting thing here from going from like 95% to a hundred percent. I'm very biased wor…”

“Obviously coding is the best application for agents because it's all the gradable. It's super important. You can make everything like API or code action, right?”

“I think making the tool good and reliable is probably like 90% of the whole agent. Once the tool is actually good, then the agent design can be much, much simpler. On the other hand, if the tool is bad, then no matter how much you put into the agent design pla…”

“What's interesting is like, and I, I've seen this in practice, it's like, it's hard to get the agent to say, to think in numbers of steps, and especially in time, because it doesn't know time. So if you tell it like, please complete under 50 steps, it won't do…”

“There's something nuanced about this data set in particular where all the edits are super short and it's like a prior that you can put into your code. But if you don't have that, then yeah, like agents tend to just keep making obnoxiously long edits”

“Agents still get confused if they have too many memories, to my point earlier about that.”

“I think for agents in general, like having a planning step at the beginning, one, just having that plan will improve performance on the downstream task, just because it's kind of like a bigger chain of thought, but also it's just such a better UX. It's way eas…”

“So I think that like real tasks are going to be much more interactive with the agent rather than this kind of like one shot system.”

“The agents are super good at using the GitHub API also, so they can do, you know, things on GitHub, like finding all of the, you know, comments on your issues or checking GitHub actions and stuff.”

“The agents are, that most people are building, Are good at following instruction, but are not as good as like extracting them from you. Yeah. So I think that will be a big unlock.”

“I think the future of agents, the way they connect to different services is going to be MCP.”

“I feel like it's still early days for us, like to try to platformatize or like try to build these, oh, there are these five horizontal pieces. And you can plug and play and build your own agent. My personal opinion is we are not there yet. In order to build a …”

“I really do think like this is just demonstrating like a thing that is going to make agents better with this model, you know, like This is a very fun way to see it, but, like, I think the thing is that it, like, has some ability to, like, course correct, updat…”

“When we are again talking about things like agents and reasoning and whatnot, I think a lot of the things are probably done on a small scale in the RL literature, in games and whatnot, and a lot of those ideas would be relevant again now.”

“What I'm trying to do with the platform is start up an internal shadow org within the company, and that's all run by agents. Effectively staffing like each business unit with agents, you know, our growth and marketing especially being the highest priority, but…”

“In, in a future world that we imagine where actually you know, maybe the majority of code is actually being written by agents that we're delegating to, you know, doing tasks in parallel. It becomes, like, critically important that you can actually, like, integ…”

“The thing that's going to make the next wave of stuff be powerful is just, like, everyone wants better agents. Everyone wants models that can, like, go off and do stuff. And, like, reasoning was kind of, like, a precursor to that a little bit.”

“Being able to have someone set principles that are then consumable by our own agents, right? Design systems and consistency. I think it's pretty surprising the degree to which even like droids can actually imitate a brand voice and style that Cal created for u…”

“A lot of users we believe should not need to prompt engineer agents, right? If your time is being spent hyper optimizing every line and question that you pass to one of these systems, you're going to have a bad time.”

“What agents will get is agents will get a series of frames and those frames will be 64 by 64. Now generally it's just going to be one frame, but you might be able to get like maybe two in a row or three in a row, and that would show an animation. And so beginn…”

“Because you don't want to just have one instance of the model operating. You want to have multiple, right? You want to be a manager of not an agent, but of agents.”

“What's changing with agents is as they gain more and more autonomy, We'll be asked to turn this autonomy into productivity, and the only way we can do that is by doing multiple things in parallel, as we've shown. The moment you do multiple things in parallel, …”

“I'm not saying, okay, go build Figma, and you, agent, are just gonna go figure out all the complexities of Figma. I think that's just not something I see happening in any near term future, even as longer range running agents start to occur and we've got better…”

“I think the value of near real time, high quality, well documented data is about to skyrocket because I'm pretty sure that nine months from now, no one is going to want to go and like look at a even like static dashboard and click around. They're going to want…”

“The agents can't call MCP very effectively because they don't have any training on tool calls, but they have plenty of training on writing code, so you tell them don't call the tool, write code to call the tool, and they do way better with it, right?”

“MCP should also enable agents, and agents are inherently somewhat stateful, and there's some form of, like, long-term communication going between, like, the client and the server, and so we always looked for something like that.”

“I think that the actual graph structure is emergent in the mind of the agent, ah, in the same way it is in the mind of the human. And that's a more powerful graph, because it actually evolved over time.”

“A few of the insights is, like, everyone, frontier model is not good at search. Humans have this natural explore-exploit trade-off, where we kind of understand, like, when to stop doing something. Also, humans are pretty good at, like, forgetting, actually, li…”

“I think like almost like every agent should have its own wiki that it's updating and that's, Persistent memory. That is a very weak knowledge graph. And you could strengthen it if you want more structure, but you may not need it.”

“There will probably eventually be things like performance level review, security review, things like that, where it's like more more different aspects of how this feature might affect your code base that you want to potentially leverage an agent to help with.”

“Agents can do three things. They can access your files, they can access the internet, and then now they can write custom code and execute it. And you really only let an agent do two of those three things. If you can access your files and you can write custom c…”

“To some extent, Dreamer does make its own tools in that agents appear to the system as tools, so they can be used to accomplish things. So you can build an agent that is essentially a tool”

“So the way I think about it is we've had four fundamental breakthroughs in functionality, LLMs, reasoning agents and then and then now RSI and they're all actually working.”

“The exciting thing about that is sort of your agent can sort of bootstrap its own software and capabilities and actually debug and maintain them.”

“That will be kind of the dominant species over the next like 10 years is, is we've moved from assembly to C to C++ to JavaScript to now like words.”

“And our belief is strongly that agents today and going forward will need all these different compositions of computers to do different types of tasks.”

“Coding has worked so well that we now have to rebuild the IDE, right? I mean, it's kind of nuts to see what we launched is like, oh my God, I have these hundred agent sessions. I, the cognitive load, it transfers back to me as a human is so excessive that now …”

“So the value creation opportunity now in the agent world is in fact, 10 X more, but it does require us to have, for example, there's going to be usage around M three six five, right? Which is going to be perhaps more than even the end users. And we have to eve…”

“If you parse some untrusted content and there is like a prompt injection, you know, something that's clearly trying to get the model to do a bad thing, you might be interested in knowing about that, but you don't necessarily like want your cloud code that you …”

“Now, things that are that simple, to be clear, are covered at this point by most agents, right? You know, they all They, despite some issues, yeah, normal, normal sort of, you know, will not be that easily fooled by just push all my API keys to a public thing,…”

“Actually, I think many of the traditional software will be sort of rewritten with this new paradigm, which is just get the data to be there. And then they slap some agent on top.”

“Instead of worrying about PostgreSQL and maybe Spark SQL, why not just one? But I don't think that's an issue for agents. Agents are very eloquent in PostgreSQL or Spark SQL. It's never going to get confused. As long as the data is there and it's accessible ag…”

“Plus the agent is like completely useless if you can't share sessions with someone and have history and have search and all this like layer on top of it for collaboration.”

“Initially, one of the biggest mistakes that people make is that they just want to throw something in an agent, and then walk away and expect to get a finished result at the end.”

“From my perspective, the way to start in a business introducing agents to a company is to give each person their own agent.”

“I think about an agent as an LLM call that is wrapped in machinery that's used to construct context. It's really a big context construction machine. And also it provides a way of executing actions.”

“Today, a lot of the demand does come from basically, like, the places where people have historically used human panels, we can basically now replace with agents. And these synthetic populations.”

“You've taken like the entire software industry and you've compressed it into this tiny bubble that the only name that people have for it is like agents, but you know that it's going to re-expand again and we're all going to find the lines that exist between th…”