The Ledger
Every statement that passed quotation and attribution checks. Mix any filter with any other: certainty 1/5, debate potential 5/5, or both at once.
why aren't all 1,824 resolved? a statement only gets an assessment when the public record can support or contradict it. opinions and what-ifs never can, and 0 checkable ones are still open, waiting for their date. predictions held up or didn't; assertions are supported or contradicted. on every card: ▮▮▮▮▮ certainty · ▮▮▮▮▮ debate potential. speakers are clickable
Proper AI harnesses enable 80% to 90% customer issue resolution rates
“If the harness is good enough, I would say, of course, it depends on the industry, but on average, you can get to 80, 90% of resolutions for, like, customer product issues, but to get there, it's the job of the harness”
AI model switching costs remain non-zero due to fragile harness optimizations
“People keep saying like the cost of switching between models is zero. It's cheap, but it's not zero because sometimes you like spend, you know, three, four months, like fine tuning exactly how the model should be, or like how the, Product should be. And then o…”
Ludwig: AI tooling creates an enormous bimodal productivity gap among engineers
“And I think in that you start to see more of a bimodal distribution of engineers, right? You start to see like, wow, there's this subset of people that they really get it. Like they're all in and they've clearly invested the hours needed to learn these tools a…”
Younis: Physical AI Bottleneck Is Onboard Deployment, Not Model Intelligence
“In the physical AI world, we're not really constrained right now by like the intelligence of the models. It's actually what Peter's talking about is actually deploying them. ... On the hardware you give you. And so, and there's just a reality is of safety crit…”
Parakhin: Effective PR review requires largest pro-level models, not fast tools
“At PR review time, you want to run the largest models. That means codex or cloud code is not going to cut it. You need to have pro-level models if you really want to stem the tide of bugs from going into production”
Parakhin: Slower AI PR reviews actually save total deployment time
“It actually, in terms of the overall time to deploy, it's total time savings if you spend more time on a longer model, like, thinking for an hour, because then you don't have to spend all that time During testing and rolling, you know, rolling back the deploym…”
Simon Last Argues That Coding Agents Are the Kernel of AGI
“I think one thing that's becoming more clear is I think like coding agents are the kernel VGI, sort of everything is a coding agent.”
Notion Engineers Faced an Identity Crisis Shifting From Coding to AI Delegation
“Every software engineer in Notion this summer went through like this sheer one of our engineering leads at the company called it like, every software engineer is going through the identity crisis that every manager goes through, where all of a sudden they real…”
Supervising AI Agents Is a Deeply Technical Systems Problem, Unlike Managing Humans
“There's a critical difference
To being a manager, which is that like, it is actually very deeply technical.
The problem of, you know, humans are very like fuzzy and you can't like treat a team of humans like a rigorous system where like, you know, PRs like fle…”
Over-Simplifying AI Agent Interfaces Abstracts Interpretability and Nerfs Agent Capabilities
“I'd actually say we don't try and make it as easy as possible to use because the more we do that, the more we abstract away that interpretability that Simon's talking about that basically nerfs the model or nerfs the agent from being super capable.”
Simon Last: 99% of Agent Failures Are Tool Bugs, Not Model Flaws
“And actually, 99% of the time, it's a bug in one of the tools. Right. And so, just fix the bug.”
Lopopolo: Reasoning models eliminate need for rigid state-machine scaffolding
“And this I think is like the fundamental difference between reasoning models and the four ones and four O's of the past where these models could not think. So you kind of had to put them in boxes with a predefined set of state transitions. Whereas here we have…”
Lopopolo: Collapsing product problems into code allows Codex harnesses to solve them
“If you can figure out how to collapse a product that you're trying to build a user journey that you're trying to solve into code, it's pretty natural to use the codex harness to solve that problem for you.”
Lopopolo: AI models can in-house 2,000-line dependencies in an afternoon
“The level of complexity of the dependencies that we can internalize is I would say low medium right now, right? Just based on model capability. What is medium? I would say like a couple thousand line dependency is a thing that we could in house no problem in a…”
Lopopolo: AI-amplified small teams require extreme package decomposition and strict boundaries
“The structure of the repository is like, 500 NPM packages. It's like architecture to the access for what you would consider, I think, normal for a seven person team. But if every person is actually, like, 10 to 50. Then the, like, numbers on, like, being super…”
Lopopolo: Autonomous Coding Removes Human Language Familiarity Constraints
“No humans in the loop here. So like my, Own personal ability to write or not write Elixir doesn't really have to bias us away from using the right tool for the job, which is just wild.”
Lopopolo: Converting UI Images to ASCII Art Improves AI Agent Layout Perception
“If we want to actually, like, make it see the layout, it's almost easier to rasterize that image to ASCII arc and feed it in to the agent.”
Lopopolo: Native code guardrails outlast external model scaffolds as AI advances
“If we were building an entire separate Ross scaffold around Codex to restrict its output, that I think would be like additional harness that would be prone to being scrapped. But yeah, if instead we can build all the guardrails in a way that's just native to t…”
Andreessen: Modern AI agents are simply LLMs combined with Unix primitives
“So it turns out what we now know is an agent is the following. It's a language model. And then above that, it's a bash. It's a bash shell. So it's a Unix shell. And then the agent has access to the shell and, you know, hopefully in a sandbox, maybe in a sandbo…”
Andreessen: Bot screening is impossible; proof of human is necessary
“The bots can pass the Turing test. And if the bots can pass the Turing test, then you can't screen for bot. You can't have proof of not a bot, but what you can have is you can have proof of human.”
Andreessen: Utopians and doomers overestimate how quickly humans adapt to AI
“Both the AI utopians and the AI doomers are far too optimistic. You see what I'm saying? Because they believe that because the technology makes something possible, that eight billion people all of a sudden are going to change how they behave, and it's just lik…”
Sun: Embodied General Intelligence Requires Interactive Causal Data
“On our way to, let's call it embodied general intelligence, Models need to learn the consequences behind their actions, which means that they need interactive data.”
Manning: Mainstream vision models fail by operating solely on pixel surfaces
“Believing that there can be a really rich connection between a more symbolic layer of abstracted understanding of visual domains, which aren't in the mainstream vision models, which are still trying to operate on the surface level of pixels.”
Manning: True World Models Require Action Conditioning and Semantic Abstraction
“You only actually have a world model if you can predict, given some action is taken, what is going to change in the world because of that, and in particular that becomes hard over longer time scales, so if you're simply, you know, trying to predict the next vi…”
Manning: Semantic abstractions require five orders of magnitude less data than pixels
“If there are ways in which you can work with five orders of magnitude, less data than people working purely from pixels, you're going to be able to make a lot more progress, a lot more quickly, and that's the bet here.”
Lample: Specialized AI models are more cost-effective than monolithic models
“That's why we can actually use models audio, but also like OCRs that are like really, really good at that, and that will be much more cost effective than a general model. That will contain a lot of capabilities you don't really need.”
Lample: 1B to 3B parameter models are optimal for speech transcription
“For instance, for audio here, if you want to do transcription, I think it makes no sense to use a model as this large. If you just want to transcribe tech, it would be very inefficient. Like if you want to do audio, you probably just want to do the one B or a …”
Lample: Long-horizon RL trajectories require new algorithms beyond GRPO
“GRPO, for instance, it doesn't really work with any bit of policy, which was okay initially, because you are solving math problems that can be solved in like a few thousand tokens, so the model can actually generate them pretty quickly, so when you do your upd…”
Kulik: AI for materials is at 'ground zero' on manufacturing processing
“Most people who actually work on
Getting materials to the device scale, say something that would be in your television or something like that, is they will tell you that it's not just the material, it's the process.
And I think we're at ground zero.
We're nowh…”
Kulik: Literature breakdown temperatures from graphs frequently contradict authors' text descriptions
“One of the funniest things I think we noticed is that you can get the temperature at which a material will break down two ways. One, you can get it from the graph, and two, you can get it from what the authors say about how they interpret the graph. And those …”
Singleton: TypeScript is the optimal language for AI-driven development
“TypeScript is an amazing language for AI because there's tons of training data. In the models and it's strongly typed. And actually at the company, we built most of the stack in TypeScript, and we have this amazing property, which is we have type safety all th…”
Singleton: Dreamer replaced Vector DB RAG for agent memory due to complexity
“Very early on, we were putting lots of facts into a vector database and doing embeddings and pulling them back out using, you know, reverse look of embeddings. Rag that actually worked, but turned out to be much more complexity than was actually required. So, …”
Singleton: Hands-on engineering managers have the ideal skill profile for AI orchestration
“It turns out being an engineering manager, as long as you stay very close to the code and are able to continue to craft it yourself, is actually a great skill profile for being able to make agents work for you and for your team in this in this age.”
Rieseberg: AI agents need parity with all user tools
“I think that entity needs to have access to all the same tools you have access to. Otherwise it's going to be hamstrung, like all these complex ways.”
Rieseberg: Sandboxing bypasses need for 100% model alignment
“I don't think we need to wait for like a hundred percent model alignment. We can rely on the same Swiss cheese model we've used in the industry for a long time, but I do think we need to like universally, maybe eventually invest more. And that's what we're doi…”
Colvin: LLMs are 100x faster under four specific engineering conditions
“My take is that there are four, four things where if you can cover all four of these things, LLMs are not like three X faster or five X faster. They're like a hundred X faster.”
Eskildsen: Model weights compress reasoning, not all world knowledge
“We can take all of the world's knowledge, all of the exabytes and exabytes of data that there is, and we can use those tokens to train a model, but we can't compress all of that into a few terabytes of weights, right? We can compress into a few terabytes of we…”
Eskildsen: Object-storage-first databases trade 200ms write latency for pure upside
“The only real downside to that is that if you go all in on object storage, every write will take a couple hundred milliseconds of latency, but from there, it's really all upside, right? You do the first query, it takes half a second”
Shah: OpenClaw memory fails because LLMs frequently skip search tool calls
“The way OpenClaw has with QMD or with whatever memory plugin you use, it inherently relies on tools to search through these memory.md files that it prepares. So, you know, like, what did I decide about the API? Then agent will decide to search, and sometimes i…”
Secure AI agents must restrict one of file, internet, or code access
“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…”
LLMs favor CLI tools over APIs due to massive pre-training data volumes
“I think that in pre-training, there's just an enormous amount of command line data. Like even let's ignore, let's like, let's ignore RL. Like you're doing no harness post training. Just the amount of like CLI versus API documentation for just like navigating t…”
Horthy: Top 1% of AI builders don't use popular public frameworks
“The way the top one percent build is so different from the bottom 99%. You have all your, like, indie hackers and, like, open source frameworks that are very, very popular. And, like, everyone uses, and that's what you see in public, and then you go see how re…”
Levie: Enterprises must adapt their workflows to AI agents, not vice versa
“What's happening is we are changing our work to make the agents effective in that model. The agent didn't really adapt to how we work. We basically adapted to how the agent works. All of the economy has to go through that exact same evolution. The rest of the …”
Levie: AI agents cannot succeed at search retrieval where smart humans fail
“If a really, really smart human could not do that task in five or 10 minutes for a search retrieval type task, you know, your agent's not gonna be able to do it any better.”
Huber: Frontier models repeat mistakes if failed actions remain in context
“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…”
Becker: Algorithmic Progress in AI Is Strictly a Function of Compute
“The suggestion in this paper is that if you think that algorithmic progress, you know, that, that is coming up with the transformer, coming up with RLHF, you know, MOEs, all of this stuff, better learning rate schedules is, is is itself a function of compute b…”
Becker: AI Scaffolding Value Does Not Persist Across Model Generations
“Within model generation, it's valuable, and across model generations, it's not so valuable.”
Patel: Nvidia must vastly outperform rivals to overcome vertical integration
“Google, Amazon, they get to vertically integrate, integrate, and vertical integration always saves tons of money. So he has to be better than everyone. By, not just like a little bit, by a ton. To justify his margins. Otherwise, the vertical integration of his…”