Figma Make builds real pages from prototype frames and prompts
Figma Make takes prototype interactions plus a prompt, examines the design, imports the frames, and builds the real thing, with the user able to participate and make changes afterward.
35,595 results · Most relevant
Figma Make takes prototype interactions plus a prompt, examines the design, imports the frames, and builds the real thing, with the user able to participate and make changes afterward.
Doing upfront prototype work provides better context for Figma Make or an AI agent; all decisions made in the Figma prototype carry over as context when using the prototype with Figma Make; many things done automatically in the prototype should be provided as context when building the real thing; it might be faster to visually articulate designs in Figma and pass them off as context to be built as a real prototype.
Matt Owens argues that AI can help you mechanically get to a creative outcome quicker, but it's up to you to make it a crafted, beautiful human thing that people appreciate and resonate with.
Marc Lore warns that compromising your thesis because it's too scary or risky — for example, repricing to avoid losses — leaves you in a weird place with no value proposition where nobody wants to buy. He cites sticking to the thesis that they would eventually buy diapers direct from manufacturers despite initially being unable to.
Dr. Morin disagrees with the training philosophy that you should never overload a movement because overloading slows it down. Overloading does slow the movement down — that part is true — but if you never slow down the movement, you have no way to physiologically improve strength and force, because force can only be improved by moving slower under overload. You will never improve your squat 1RM by doing squat jumps. The objective of strength training is to transfer the increased strength to speed, but first you need to slow down (overload).
The first step in addressing an athlete's weakness is to make that weakness objective with data. When acceleration lags behind top speed, jump, and strength metrics, assess acceleration objectively using metrics such as maximum force output and maximum propulsive power output on the ground.
A practitioner needs both a quantitative approach (numbers) and a qualitative approach (how the athlete moves) to diagnose sprint issues. When you have both the numbers and the video of the form, you can start thinking about what should be fixed; without slow-motion video you cannot decide where the weak point is.
Running agent code on your own computer can consume all CPU, spawn unwanted processes, delete things it shouldn't, and expose environment variables; running on a server has similar problems with secrets and your environment.
When you pause and resume the same sandbox repeatedly instead of getting a fresh image, orphaned processes accumulate over time and kill sandbox performance. Resuming old state is fast and leaves things where you left them, but the downside is leftover processes remain if you haven't cleaned up after yourself.
Running a single agent in a single session that does everything causes confirmation bias, attention dilution, context fragmentation, and recall degradation — and a larger context window does not fix it.
Hormozi argues that when you achieve what you said would make you happy and still feel dissatisfied, the problem is not an achievement gap but the wanting itself. Humans inherently want what they can't have — single people want marriage, married people want single, parents want a night off. Recognizing this structural pattern defuses the dissatisfaction.
As an adult you should eliminate alternatives: some commitments like marriage and children are effectively one-way doors, and the best things in life come on the other side of such commitments.
Hormozi warns that allowing life to make your priorities for you leads to sitting passively by while options expire — like an ant dying next to a pile of crumbs it never ate. He recommends catching yourself passively letting options expire and instead actively choosing, cutting off one future, and choosing your regrets deliberately or they will be chosen for you.
The word 'decide' comes from Latin 'decidere', to cut off. Making a decision or trade means eliminating one possible future, and you have to accept that rather than trying to keep every option alive.
Keeping your options open is itself a form of deferring living. Society overemphasizes optionality, but refusing to commit means dying with a pile of crumbs you never ate — options are worthless if never exercised.
You have to reconcile which one you are: still clinging to the optionality of youth, or having decided to become an adult through commitment. The two goals are at odds, and maturity is measured by the number of commitments you've made and the number of people who rely on you.
Life is zero-sum with respect to time. Investing an hour in one of your priorities necessarily pulls an hour from another, so you must accept the trade rather than pretend you can have everything.
Hormozi frames life as a larger game with roughly 10 component categories (health, relationships, career, etc.). Winning requires ranking them for yourself, recognizing that you cannot max all of them, and treating each as a component of the larger game rather than making one category your entire game.
Philipp Schmid describes how agents can build their own environments and be turned into shareable agents for users or customers, without writing Terraform or thinking about Kubernetes, microservices, or Firecracker.
Goodwin explains that when a hard problem has intrinsic latency in its execution step, accelerating the thinking that precedes the experiment shifts the bottleneck to the experiment itself — 'now we're just experiment bottlenecked, we're compute time bottlenecked.' He extends this: a lot of hard problems in the world look like chip design — lots of automatable cerebral thinking followed by intrinsic wall-clock latency in execution. When a workflow has a wall-clock-time-bottlenecked step, you will generate a lot of reasoning tokens before executing that step.
Choose sources → to get a library of your own and a daily brief.