Recommendation · MoneyThree concrete audit instructions: track down every long-lived token agents can read, figure out how many agents can find access to production or around current limits, and check where agents actually execute — sandboxed, managed, or wild on laptops.
AI Engineer · Your AI Isn’t the Problem. Your Infrastructure Is. — Jiachen Jiang, Coder
Recommendation · BodyJake Tuura recommends heavy slow resistance or isometric holds to squeeze excess fluid out of an overloaded tendon in the short term. Isometric holds on an overloaded tendon provide immediate pain relief and help normalize fluid distribution in tendon cells, though he says the exact mechanism is not known.
mechanism not exactly known per speaker
Garage Strength · How To Make Weak Tendons Strong w/ Tendon Expert Jake Tuura
Recommendation · MoneyDr. Fei-Fei Li advises that when using an AI chatbot, you should state who you are — profession, age, interests — in your prompt, and you can even upload an image as context. Because the algorithm mathematically incorporates the context you provide, the same question gets a different, customized answer depending on that context.
Andrew Huberman · Using AI to Increase Your Intelligence & Enrich Humanity | Dr. Fei-Fei Li
Recommendation · MoneyDr. Fei-Fei Li recommends using AI in healthcare: LLMs can mine health information well because medicine has constrained rules; AI can help disambiguate symptoms like vertigo vs. low blood pressure; AI tooling that doctors also use enables zero-cost symptom consultation; and AI can be taken advantage of for people who don't have immediate access to doctors. She also envisions presenting health information to patients so they can participate from diagnosis to treatment, and using AI to help solve disease and come up with new rules for discovery.
Consequential creator advice requires independent verification before Today can promote it.
Andrew Huberman · Using AI to Increase Your Intelligence & Enrich Humanity | Dr. Fei-Fei Li
Recommendation · SocialInstead of saying you're approaching girls, the coach recommends saying something like: 'I was actually just walking around the park, enjoying my day so far... I need to get outside and at least socialize a little bit.' This conveys the same story without blatantly telling her you're approaching cute girls.
Coach Kyle · Will He Get Rejected After Approaching This Woman? (Infield)
Recommendation · MoneyThe big-picture change: move from the 3-4 hour marathon format to a structured webinar, following the agreed structure. Live proof people are optional — you can bring up live people during launches to do the proof for each point if you want, but the same webinar works without them.
Alex Hormozi · If You Hate Selling, Please Watch This | Scale or Fail
Recommendation · MoneyAlex advises Caleb that in terms of scale, usually you go all in on door to door — it's what you're good at. 'I don't think we need to be cute about this... and just get really violent with it.' Caleb committed: 'I'm just going to full focus on this.'
Alex Hormozi · How I Would Build a $10M Service Business (If I Had to Start Over)
Recommendation · MindHormozi warns against sharing someone's disclosed information with anybody else, because if that person gets hurt by it, they still won't trust you and you gain a reputation of someone whose loose lips sink ships.
Alex Hormozi · How The Top 1% Actually Think About Trust
Recommendation · MoneyThe first move for AI search visibility is creating high-quality transactional content on your website: directory-style roundups and versus articles. This is where to start before pursuing offsite tactics.
Startups For the Rest of Us · Episode 853 | How to Become the SaaS That AI Recommends
Recommendation · MoneyRoss Hudgens describes how percent visibility in GEO is measured: use prompt trackers with proxy search volume for prompts like 'what is the best X software for your industry', and track that over time. He recommends creating categories around each of your product use cases if you can, and tracking visibility over time.
Startups For the Rest of Us · Episode 853 | How to Become the SaaS That AI Recommends
Recommendation · MoneyThe creator recommends running many agentic coding threads in parallel using coding harnesses from the labs, and argues the limiting factor is the human's brain — how much context you can keep in mind to keep all threads going. Agents also let humans work and think at a higher level, exercising more executive function.
AI Engineer · https://www.youtube.com/watch?v=nSkmXakJ6eo
Recommendation · MoneyThor Schaeff recommends trying the Gemini Live model through Google AI Studio as the easiest way to get started: select the Gemini 3.1 Flash Live model, pick a voice such as Puck, enable grounding with Google Search for real-time information, and optionally try the Live Translate model; ai.dev/live is an alternative URL.
AI Engineer · Can Your Agent Hear You Now? Building Live Voice Agents with Gemini — Thor Schaeff
RecommendationFuad Ali recommends using harness-as-a-judge for access checks by connecting it to external systems so it can call out and verify whether the user was allowed to do what the trace shows.
AI Engineer · Building Self-Learning Loops for Your Agent — Fuad Ali, Arize AI
Recommendation · MoneyForrester argues you probably need both input guards and output guards from a security standpoint — together they catch 80 or 90% of what you need. Challenge five was an output guard, a general prompt-based guard: you can do it and it's worth doing, but you will pay the cost of LLM processing. Challenge six was an input guard, which can be done upstream — probably cheaper because it doesn't get processed by the LLM. Upstream filtering helps keep performance going in AI workflows, as long as you don't muddy the waters.
The 80-90% coverage figure is the speaker's rough estimate.
AI Engineer · Build a Platform and Watch It Burn — Michael Forrester, Accenture & Whitney Lee, Datadog
Recommendation · MoneyThe presenters advise that if a tool like the search help library is not actually helping, remove it from the application, and to use the Langfuse skill with repository context to fix issues in the code — not only in the evaluator setup — so the application itself gets back to working. After finding issues in traces, fix them to improve the application over time and address the issues actually coming up.
AI Engineer · Continuously Improving Agents with Langfuse — Annabell Schäfer & Lotte Verheyden, ClickHouse
Recommendation · MoneyWolfram Ravenwolf recommends running five evaluation runs per benchmark with WolfBench (more if budget allows) and publishing all evaluation results so others can inspect them.
AI Engineer · From Zero to Leaderboard: Agent Evaluation — Wolfram Ravenwolf, Weights & Biases
Recommendation · MoneyTreat the WolfBench leaderboard as more than a chart: load a snapshot, add your own runs, filter metrics and models, reorder or remove bars, and export. The interactive page lets you build custom reports, copy charts elsewhere, use the screenshot symbol to share results (e.g., on X), and share the URL so others see exactly the view on your screen.
AI Engineer · From Zero to Leaderboard: Agent Evaluation — Wolfram Ravenwolf, Weights & Biases
Recommendation · MoneyLet AI agents automate your full workflow from beginning to end: observe issues, pull them down, create datasets, build fixes, and test them. The agent can pull down traces, review evaluations and annotations, do its own analysis, and come back with fix suggestions autonomously, including future suggestions like asking more questions or adding guardrails.
AI Engineer · Let Your Agent Cook: Using Skills to Evaluate and Improve Your App — Ankur Duggal, Arize AI
Recommendation · MoneyDuggal recommends setting up evals — LLM-as-judge, code-based evals, or some other eval setup — as the way to move beyond shipping on vibes.
AI Engineer · Let Your Agent Cook: Using Skills to Evaluate and Improve Your App — Ankur Duggal, Arize AI
Recommendation · MoneyThrough the repo you can set up your own cluster and configure it in any way you want; the infrastructure is not strict and can be self-hosted, and with your own GPUs it is totally your own.
AI Engineer · https://www.youtube.com/watch?v=Ndp5VaqFrl0