37,617 results · Most relevant
Bakken discourages going on and off strength training because it creates a relative load from entering training you're not used to. He recommends scheduling strength work on the same day as the X (interval) session and following it with a slightly longer cool down to help bring muscle tone down.
Bakken endorses treating hill training as an X (hard) session. Doing hill sessions as threshold sessions slows you down instead of getting as close as possible to race pace without negative effect, and the host notes that doing 3-minute hill intervals as a threshold-style session derailed his own training.
hedged
Marius Bakken says you can actually feel muscle tone by getting used to palpating it on your quads, and you can get a feel for it by walking up the stairs every day and noticing how the legs are feeling — the most practical way of doing it. He calls this the stair test, a really good way of monitoring muscle tone from day to day. The second monitoring signal is springiness on the actual sessions — how springy or light you feel each step. More complicated monitoring like lactate compared to heart rate and pace exists but is not necessary; the stair test, how you feel on the session, and how it evolves during the session are the most important things.
hedged
Commercial context: The creator presents this as their own offering and directs viewers to get it.
Bakken recommends shifting to more marathon-specific work from about 6 to 12 weeks before a marathon (or 4 to 10 weeks), meaning longer, more durable sessions.
Dr. Marius Bakken recommends running threshold sessions at about 80 to 87% of max heart rate — comfortably hard. Without advanced measurement, use a speech test: a pace where you can say three to five words in a sentence before going after your breath.
Dr. Marius Bakken recommends putting in as much volume as you can on sub-threshold work while controlling intensity, and running easy volume below 70% of max heart rate. The goal is to run fast enough to get a real running-economy effect without going hard enough to incur the negative effects of running above threshold.
Dr. Marius Bakken recommends that for a normal athlete training for 5K/10K, two of the four or five weekly running sessions should be sub-threshold work.
The speaker advises reading real AI outputs, which evals make possible: setting up the right eval tools let Bumble see what real users were receiving and whether the prompt was doing a good job. Bumble's success criteria changed from overall green-versus-red results to examining the long tail of data — whether different segments of users receive feedback well, including whether women respond the same way as men and whether users in different countries respond the same way, since language generated in French may differ from English.
maybe the language generated in French is different from the language generated in English
The guest recommends enterprises use deterministic controls — sandboxes and human-in-the-loop approval gates — to feel safe deploying computer-use agents, even when the model itself is highly aligned.
Masaba Gupta advises making everything on brand and never going off brand, keeping the storytelling and language the same across all brand touch points — she calls it the brand's 'body language'. She stresses that the story created in the head office must permeate all layers of the brand: retail, e-commerce, social media, communication, and all touch points, and that when sitting down with each team, whether creative or retail, she delivers a singular message.
Zach Lloyd recommends defining your software factory in code, with a strict definition covering the workflows, the skills, the MCPs, and where these run. Version-controlling the factory definition lets you test different versions of your factory and lets coding agents update your factory. He suggests having an actual code repo that sits behind the factory, where you can see a definition of the entire factory at any given point in time, including everything that goes into automating development: agent definitions, automations, benchmarks, where agents run, the skills, and the webhooks — all stored in a repo that allows for automation.
Zach Lloyd recommends setting up a self-improvement loop where agents look at failure modes, aggregate them, look for patterns, and come up with ideas to improve the factory definition. Agents can propose fixes to failure modes via a PR to the factory definition. One example fix is having agents re-read matching repository skills before implementing. He frames closing the loop — agents identifying problems and then fixing them — as a core concept for improving development.
Zach Lloyd recommends storing the entire factory definition in a code repo that allows for automation, including agent definitions, automations, benchmarks, where agents run, skills, and webhooks. He argues that defining the factory in code and version-controlling it enables testing different versions of the factory and lets coding agents update it — which is what enables the factory to improve itself.
Standardize evaluation infrastructure (reusable frameworks, metrics, judges calibrated with human feedback); automate feedback loops (continuous trace collection, recurring failure detection, root cause analysis); scale automated optimization (prompt optimization, agent reflection, repeatable candidate testing); validation and trust (holdout evaluations, regression testing); and democratize RSI with reusable components and self-service info.
Start with prompt updates as the easiest and most straightforward way to iterate; then optimize the structural context of the AI system; then expand scope to automatically design the entire workflow (meta information design); then optimize the harness code itself; and finally, the most complex step, optimize the optimizer code itself.
The RSI process proceeds in ordered steps: (1) run the agent and generate samples — for the career agent, given a query, generate output and log the process in traces (e.g., LangSmith traces); the agent trajectories and traces generated are the material used for optimization. (2) Run the traces through the evaluation engine (e.g., the LLM judge) to get judge output telling where the system is good and where it is not, to guide future iteration. (3) Agent reflection (also called root causing): based on the judge output, understand the root cause of the bad output. (4) Based on the identified root cause, generate an edits proposal — currently the edits are prompts, but in future they can be new workflow designs, harness code, or optimizer code. (5) Validate the edits, because some edits can
Dustin advises limiting SaaS demos to no more than three features — never going over three — and picking out the features you're going to demo in advance. When you have a large feature set and limited demo time (30-40 minutes), he recommends scoping down to drive home key points. He cautions against letting prospects drive the feature selection, because you end up so in the weeds with your technical baby that it derails the demo.
Dustin Perrier says you need to have a next action from every demo, and that you need to send a follow-up email the same day as the demo, with a little area you can personalize. He also recommends putting demo prospects into a drip campaign, because they may be busy after the demo and forget how wonderful your product is.
Dustin Perrier argues that problem statements are horrible because they're not emotional, and that a problem statement won't draw prospects into your conversation and presentation. Instead, he recommends crafting a story that walks prospects through: this is the problem I experienced, this is why I wrote this software, this is what it solved and what it hasn't solved.
Dustin Perrier argues that roughly 20% of a demo should linger on the intro slide of the deck, using that time for discovery instead of powering through the deck. He advises not proceeding until you have verifiable data that the prospect is engaged, and suggests using the intro slide as the conversation point where you take notes on prospect concerns and what you need to show to address them.
Choose sources → to get a library of your own and a daily brief.