mary

Judging by my tl there is a growing gap in understanding of AI capability. The first issue I think is around recency and tier of use. I think a lot of people tried the free tier of ChatGPT somewhere last year and allowed it to inform their views on AI a little too much. This is a group of reactions laughing at various quirks of the models, hallucinations, etc. Yes I also saw the viral videos of OpenAI's Advanced Voice mode fumbling simple queries like "should I drive or walk to the carwash". The thing is that these free and old/deprecated models don't reflect the capability in the latest round of state of the art agentic models of this year, especially OpenAI Codex and Claude Code. But that brings me to the second issue. Even if people paid $200/month to use the state of the art models, a lot of the capabilities are relatively "peaky" in highly technical areas. Typical queries around search, writing, advice, etc. are *not* the domain that has made the most noticeable and dramatic strides in capability. Partly, this is due to the technical details of reinforcement learning and its use of verifiable rewards. But partly, it's also because these use cases are not sufficiently prioritized by the companies in their hillclimbing because they don't lead to as much $$$ value. The goldmines are elsewhere, and the focus comes along. So that brings me to the second group of people, who *both* 1) pay for and use the state of the art frontier agentic models (OpenAI Codex / Claude Code) and 2) do so professionally in technical domains like programming, math and research. This group of people is subject to the highest amount of "AI Psychosis" because the recent improvements in these domains as of this year have been nothing short of staggering. When you hand a computer terminal to one of these models, you can now watch them melt programming problems that you'd normally expect to take days/weeks of work. It's this second group of people that assigns a much greater gravity to the capabilities, their slope, and various cyber-related repercussions. TLDR the people in these two groups are speaking past each other. It really is simultaneously the case that OpenAI's free and I think slightly orphaned (?) "Advanced Voice Mode" will fumble the dumbest questions in your Instagram's reels and *at the same time*, OpenAI's highest-tier and paid Codex model will go off for 1 hour to coherently restructure an entire code base, or find and exploit vulnerabilities in computer systems. This part really works and has made dramatic strides because 2 properties: 1) these domains offer explicit reward functions that are verifiable meaning they are easily amenable to reinforcement learning training (e.g. unit tests passed yes or no, in contrast to writing, which is much harder to explicitly judge), but also 2) they are a lot more valuable in b2b settings, meaning that the biggest fraction of the team is focused on improving them. So here we are.

Where are the consumer app founders in SF?

where are the consumer app founders in sf? i lowkey have three iOS apps live in the app store right now but haven't built up the gumption to start marketing them yet looking for buddies tbh

Where are the consumer app founders in SF?

Meta Harnesses is Autoresearch on steroids. Something I've been exploring recently is to get long running agents to hill climb on a verifiable task to continuously improve without my intervention. Karpathy's Autoresearch did this pretty well on specific tasks, but this weekend I tried Meta Harnesses which moves one level of abstraction up. What does Meta Harness do? Autoresearch can be used in harness like Claude Code / Codex to generate experiments to try, evaluate results, and continue looping. Meta Harness generates a harness itself that optimizes on a task or a set of task. Here, we define a harness as "a single-file Python program that modifies task-specific prompting, retrieval, memory, and orchestration logic". The idea is that LLMs are very powerful today, but to harness [pun intended] their power, you need to give it the right prompts and context. Meta Harnesses automates coming up with the right prompts and the right way to retrieve context to solve a problem. Where did this idea come from? This is from a paper from Stanford and the author of DSPy written last week. The paper shows fantastic performance on 3 tasks: text classification, math reasoning (IMO level problems) and coding (Terminal Bench 2.0), far outperforming traditional harnesses. The discovered harnesses are interesting: math for example, splits up the logic into different categories (Combinatorics, Geometry, Number Theory, Algebra) and prompts and looks at the context differently. The coding harness, amongst other things, pre-processes the tools available in the environment to save exploratory turns. When should you use and not use it? Meta Harnesses seem pretty useful for tackling a specific but wide set of problems where the result is verifiable. In contrast, when I tried it on a specific task like Chess, it arbitrarily divides the problem into separate tasks - opening, mid game, end game, and creates different approaches for each. This "works" but isn't really clean because we believe there should be one approach that does all three. It does far better on things like examinations (JEE, Gaokao) where it splits problems into categories and tackles each category with different strategies. This paper covers a pretty light version of what a harness means. In the future, we can split up tasks into harnesses that have access to specific kinds of data, specific toolchains and various models to get even better results. Overall, pretty cool applied AI approach to hillclimb a verifiable task in a specific domain with variety within the problem space.

💡 What if the most important learning space in LLMs isn't in the weights but in the context itself? Most people hear this and say: "oh, so just prompt optimisation." That framing misses what's actually going on. The context window is not just input. It is a parameter space where small token changes can completely shift the model's behaviour. Unlike weights, context can be built up incrementally, reversed trivially, inspected and interpreted, and small token changes can dramatically shift the output distribution allowing rapid adaptation. ❌ This isn't context engineering (humans designing prompts, instructions, data or tool access). ❌ And it's not in-context learning, where the model learns from examples in a single forward pass. ✳️ This is autonomous learning that happens directly in the context itself. The model can rewrite it, improve it over time, and optimise it using feedback, error and search. 🔄