Recommendation · MoneyTeams shipping agents must continuously mine for signals where things are going wrong and make sure they don't happen again. Monitor aggregate metrics on what is going on and detect signals where things are going wrong. Monitoring should include finding the interesting traces you want to dig deeper into, not just aggregate metrics. Track quality signals such as compliance guardrails, truthfulness, and how many users are frustrated (e.g., writing all-caps messages).
endorsed
AI Engineer · Evals for High-Stakes AI Agents — Doneyli De Jesus & Annabell Schäfer, Langfuse
Recommendation · MoneyAnnabell recommends being in favor of working with your coding agents to continuously improve your applications — but warns against two extremes. Don't just ask your coding agent to 'fix my agent, make no mistakes', which produces slop rather than anything helpful; if you fully automate agent improvement and just let the agent go for it, you will end up with a low-quality system and unsatisfied customers. But also don't go the full manual way anymore — don't instrument yourself, catch all failure modes yourself, or review all the data yourself; these can be automated.
AI Engineer · Evals for High-Stakes AI Agents — Doneyli De Jesus & Annabell Schäfer, Langfuse
Recommendation · MoneyRun the process manually in parallel with the agent (shadow runs) to compare how the agent handled it, measure accuracy, and build ground truth. Start with a fully human-in-the-loop system, then over time slice the data into parts you're confident to automate versus things where you always want a human in the loop.
AI Engineer · Evals for High-Stakes AI Agents — Doneyli De Jesus & Annabell Schäfer, Langfuse
Recommendation · BodyAttack acceleration first when working on sprint technique, because in most sports the max speed phase won't express much difference. Unless you're a winger getting big open breaks covering 40-50 meters, max speed matters less. Getting good at acceleration is the low-hanging fruit and big bang for your buck for most athletes.
Garage Strength · How To Get Strong and Still Be Athletic w/ Sika Strength
Principle · MoneyIn regulated spaces, define hard limits — things that definitely shouldn't happen (e.g., a financial services agent should never give investment advice) — and ingrain them in the evaluation set. Even if a violation is never fully prevented, you will at least know about it when it happens.
AI Engineer · Evals for High-Stakes AI Agents — Doneyli De Jesus & Annabell Schäfer, Langfuse
Report · MoneyThe proposed alternative is an application-specific passive device where the physics of light propagation performs a step of the diffusion procedure; by iterating on the optical system architecture, one can start from a random distribution of pixels and, just by letting the physics do its work, create new samples from the desired dataset.
Y Combinator · What If We Stopped Using GPUs? | YC Paper Club
Method · BodyAssess foundational strength first as a simple ratio to bodyweight, taking into account the athlete's current level and training status, and decide whether strength needs to be a priority. If strength numbers are already adequate for the goal, move to the second phase: the technical aspects of the movement or sprint — altering patterns, bringing in accessories or derivatives, and changing how the athlete runs or moves.
Method, not a verified protocol.
Garage Strength · How To Get Strong and Still Be Athletic w/ Sika Strength
Method · BodyFor improving conditioning on the air bike: do 10 sets of 10 calories or one set of 100 calories once or twice a week, intensely; the same workout week to week with genuine effort produces good progress without elaborate programming. For longer work, do 60-90 minutes of long slow distance keeping heart rate at 70%, or interval work of six by six minutes at 85-90% heart rate without going above that ceiling, and occasionally push past threshold into the zone where you feel like you are about to die. You can get an excellent conditioning session in under 10 minutes.
Endorsed protocols from the guest
Method, not a verified protocol.
Garage Strength · How To Get Strong and Still Be Athletic w/ Sika Strength
Report · MoneyVlad Tenev describes Robinhood Ventures Fund One, structured as a publicly traded venture capital firm: capital was raised in an IPO from Robinhood customers via Robinhood's IPO channel, then used to invest in startups, and the fund trades on the New York Stock Exchange just like a stock. The fund holds ultra late-stage privates including OpenAI, fintechs, a lot of AI companies, 11 Labs, and Cruzeau. Robinhood Ventures Fund 2 partners with YC to give people exposure to the earliest possible stage (seed and series A), where the risk is highest but the opportunity is also greatest, and is run by Rich Aberman.
No Priors: Artificial Intelligence | Technology | Startups · Tokenization, Agentic Trading, Harmonic: Robinhood's Mission to Expand Ownership with CEO Vlad Tenev
Report · MoneyVlad Tenev announces Robinhood Agents, unveiled at Hood Summit, which puts the agent harness and entire UI inside a Robinhood account. He describes it as like a Claude Code or Codex-style tool optimized for trading, with skills such as portfolio rebalance and other trader-native capabilities. Robinhood also launched an agent app store where users can connect to sources like satellite data to build strategies such as counting cars in retailer parking lots.
No Priors: Artificial Intelligence | Technology | Startups · Tokenization, Agentic Trading, Harmonic: Robinhood's Mission to Expand Ownership with CEO Vlad Tenev
Report · MoneyThe most promising near-term direction in neuromorphic computing is the commingling of memory and compute, done purely digitally, where a bunch of startups are working. One approach is combining SRAM and logic. D-Matrix is a startup that has done good work here, including a strong Hot Chips presentation; its innovation is essentially co-packaging: bringing SRAM very close to compute in the memory hierarchy on the decode side to address the decode ceiling. IBM has also done work in this area. D-Matrix feels like a makeable-now digital memory-compute company: it works, it can be manufactured, and the market can take it up. However, co-packaging SRAM close to compute increases the surface area of the packaging, which means fewer servers fit in the same amount of data center space, and the do[
Y Combinator · What If We Stopped Using GPUs? | YC Paper Club
Recommendation · MoneyDoneyli recommends monitoring for security risk flags where the agent might have given investment advice to customers, and filtering traces by categorical scores (e.g., security risk = investment advice) to find specific examples where the agent was flagged. In his example, 89 cases over the last seven days involved customers asking for investment advice.
AI Engineer · Evals for High-Stakes AI Agents — Doneyli De Jesus & Annabell Schäfer, Langfuse
Recommendation · MoneyDoneyli recommends building a dashboard of metrics to report to business stakeholders based on data collected from the agent. Track the number of agent interactions that didn't need to go to a human agent as a business-benefit metric, and calculate the cost of agent-handled interactions versus human agent cost to show directional business benefit. Also pinpoint the areas where the agent is tripping up by tracking failure modes in order of occurrence, and track thumbs up / thumbs down customer feedback displayed in an easy-to-consume dashboard.
AI Engineer · Evals for High-Stakes AI Agents — Doneyli De Jesus & Annabell Schäfer, Langfuse
Recommendation · MoneyImpersonate different client types (e.g., everyday customers and ultra high net worth individuals) to test whether the agent respects guardrails for those personas.
endorsed
AI Engineer · Evals for High-Stakes AI Agents — Doneyli De Jesus & Annabell Schäfer, Langfuse
Recommendation · MoneyCurate a red-teaming dataset that looks for prompt injection attacks and any attack that would allow someone to circumvent guardrails and get information they shouldn't. Also curate datasets specific to a use case — e.g., knowing which cases have been disputed and whether the dispute has not been solved.
AI Engineer · Evals for High-Stakes AI Agents — Doneyli De Jesus & Annabell Schäfer, Langfuse
Recommendation · BodyWhen combining strength training with running, program two to two-and-a-half to three gym sessions per week for deadlifting or general strength work.
Garage Strength · How To Get Strong and Still Be Athletic w/ Sika Strength
Recommendation · BodyGet kids to front squat, back squat, clean, snatch, deadlift, walking lunge, and run sprints instead of spending time on gimmicky brain-training warmups; a coach who spends five years on such gimmicks instead of fundamentals ends up worse, not better.
Garage Strength · How To Get Strong and Still Be Athletic w/ Sika Strength
Principle · BodyThe 50-calorie and 100-calorie air bike tests are useful conditioning benchmarks for field sports. Around three minutes for 100 calories indicates good conditioning depending on the sport's demands; about a minute for 50 calories means you are a beast. Nobody reaches the three-minute 100-cal mark without significant conditioning time — it cannot be faked. The 50-cal times converge more across sports than 100-cal times, and benchmarks differ by sport (a front row rugby player will not match a jiu-jitsu or judo athlete). The test is low impact the day after, so you can still squat the next day.
Publisher-reported benchmarks; sport-dependent
Garage Strength · How To Get Strong and Still Be Athletic w/ Sika Strength
Principle · BodyThe host uses A-skips and B-skips as a proxy drill to assess and develop sprint coordination, bounciness, and body awareness. If A-skips become bouncier and springy and B-skips become more cyclical and smooth, sprint quality will very likely improve down the line. Conversely, a B-skip that looks like the hamstring is about to tear off signals poor sprint technique. He notes A/B skips benefit athletes for roughly their first six years of training, are a great tool for teaching middle school kids rhythm and timing, and are used by sprinters like Noah Lyles for warm-ups, while acknowledging ongoing debate about their value in track and field specifically.
Host's confident heuristic; he acknowledges debate around A/B skip drills in track and field
Garage Strength · How To Get Strong and Still Be Athletic w/ Sika Strength
Creator perspective · MoneyAn oversized decoder can play the game by itself — if you zero out the spikes, the decoder can still play with enough biases. If the silicon decoder overfits, the cells never learn — they can keep their stochastic behavior while the decoder plays the game for them. It is very easy to cheat performance out of these systems: massively oversize your decoder, run backpropagation on it, and suddenly you have brain cells that play anything. Startups and companies get this wrong a lot of the time. In fly-brain connectome experiments, people use massively oversized decoders, so it is never the fly doing anything, just silicon. The fix was to massively undersize the decoder, run ablations to confirm the spikes carry information, and set the linear decoder's bias to zero; undersizing gave better
Presented as the speaker's strong claim based on their experience; the fly connectome example is attributed to 'people' generally.
Y Combinator · What If We Stopped Using GPUs? | YC Paper Club
