35,595 results · Most relevant
Nyah Macklin shows how to set the fixed size splitter to chunk size 500 with chunk overlap, define sample node types (technology, concept, example, process, challenge, benefit), define relationship types (related to, part of, used in), and structure the graph with node-relationship-node patterns.
Nyah Macklin outlines the overall knowledge graph construction process: gather data sources, chunk the data, vectorize it, extract nodes and relationships using an LLM (prompting for JSON output), parse the JSON, and generate the graph — noting that LLM extraction cuts down time versus doing it manually.
Do 10 sets of 10 calories or one set of 100 calories on the air bike every week or twice a week, done pretty intensely, and you will improve your conditioning without a doubt. You can get an excellent quality conditioning session in less than 10 minutes that makes genuine progress.
The speaker recommends creating an agent that looks inside the code base, identifies opportunities for deduplication of code, and creates a series of issues for you.
The speaker recommends using Orchestrate when modifying an API in a microservice that requires a downstream change, to make cross-repo changes simultaneously with several agents.
Gabriel Martinez recommends breaking features into small atomic pieces small enough to hold in your head, rather than requesting a whole feature set in one shot without understanding what you're asking for. Decomposing needs into the simplest chunks lends to understanding of simpler code surfaces and control of code bases.
Creator advice attributed to Gabriel Martinez.
Gabriel Martinez recommends centering rewards around producing value, elegant well-factored pragmatic system design, and clarity of tests and evaluation harnesses, and making accountability metrics visible for each chunk of work product.
Creator advice attributed to Gabriel Martinez.
Gelsinger endorses moving datacenters to 800-volt DC power delivery to eliminate the many historical AC-to-DC conversion steps in the power network — 'the revenge of Edison'. He also calls for rebuilding the entire power delivery network with solid-state transformers and switches to unlock innovation in power infrastructure, and for the US to get much more efficient at delivering the power network including expanding domestic supply chains.
Cisco guaranteed its employees that if they don't use AI, they will lose their job — the opposite of threatening that AI use would cost jobs. Patel says if you're not using AI, chances are Cisco is the wrong place for you, so go all in and the company will give you all the tooling and support. He notes that if someone did not use a PC or the internet, you would never hire them in a knowledge worker job, so not using AI in a secular shift is similarly disqualifying.
For job-specific tools used all the time, the speaker recommends generating your own plugins in Figma Motion — and instead of searching for an existing plugin or diving into countless tutorials, asking the agent to help build the plugin. They note it's easier to do than expected, and once made, the plugin can be used anytime.
Instead of rapid-fire questions, Coach Kyle recommends offering a longer, flavorful answer about yourself — e.g., 'I'm actually good. It's actually like such a nice day outside. I actually finished work early...' — delivered in a slow, relaxed way so she responds to something you said rather than you having to ask questions.
Coach Kyle recommends talking at a close distance, relaxed, holding eye contact with a smile, using a soft voice, periodically injecting a little laughter, having a moment with a nice little handshake, and gradually getting physically closer — these subtleties keep a conversation from being boring.
Coach Kyle advises getting a walking woman's attention from roughly 10 feet out instead of waiting until she is within one to two feet, framing the close-distance pop-out as a mistake.
A common beginner mistake is thinking a speed session is something that lasts two hours and can only be done once per week; speed work should be called 'speed stimulus' rather than 'speed sessions'. If you have only one session per phase, do one oriented around acceleration and one around high-speed. Add a second weekly high-speed session whose objective is not high-speed itself but hamstring prevention. For 100 meters a week of high-speed running, do one set of three times 20 meters flying 20 in one session, and another set in a second session during the week. The same volume metrics apply to acceleration training (roughly 100-150 meters of exposure); these volume targets are principles, not recipes.
volume figures are presented as principles, not recipes
In a high-speed session, do not count the build-in distance as part of the 90%+ volume — only the flying portion counts. Use 20-meter flying sprints rather than 10-meter to get more work. Do not ask for maximum acceleration, because players will push all the buttons every rep and every session, which is not what you want. Focus only on high-quality high speed; you don't care how they accelerate.
Use very intense trunk flexion exercises; everything involving trunk flexion and huge hip flexion can strengthen the hamstring and hip in bent positions, including starting positions and many lunge-type exercises. As much as possible, go with unilateral exercises to replicate the lunge and sprint movement. The drop and catch RDL is an example of a very intense trunk and hip flexion exercise he loves.
Rogan urges people not to push further away from those who disagree but to move closer and talk to them. He also calls for stopping the antagonistic us-versus-them mentality and says he does not want to align with political parties because he does not think that is smart.
Fractile keeps front-end design, physical design, back-end implementation, and advanced packaging all in-house — about 150 people, skinny in every sector of the chip stack — enabling a more agile closed loop that is very different from a prior approach with a handoff point where you're at the mercy of how the other partner behaves.
Liemandt advises putting kids through the loop: have them try hard things, get them through with whatever motivation it takes, and have them experience themselves as capable. He gives the example of having a kindergartner climb a 40-foot rock wall to show them they are capable. He also notes kids will grind through hard things — sometimes you have to figure out what the motivation is, since kids are often not intrinsically motivated because they see the task as too hard and 'not who they are.'
Joe Liemandt describes how ADHD kids can lock in for two hours in engaging apps, and that when ADHD kids only take two hours a day of academics, ADHD stops being a problem because they spend the afternoon building. He recommends asking parents of ADHD-diagnosed kids: can he play a video game for 25 minutes straight? If yes, the kid can focus when engaged. They use 25-minute Pomodoro blocks for ADHD kids, and in the worst case, at the sports academy they run ADHD kids before the apps to solve engagement issues.
Choose sources → to get a library of your own and a daily brief.