How I AI
Everything How personally uses, recommends, or has created — plus things they don't recommend — sourced from their own show and appearances on other podcasts.
Top picks
Ranked by repeated personal use, excluding sponsorships.
Warned against
"I threw Claude code at this. Claude code could not figure it out even with Opus"
"I've only done about two or three things in Claude design and I am blocked until Saturday and it is Tuesday. $200 later, we are back."
"Yesterday, I used the Xbox Game Bar thing to record a video off my screen. Well, for 10 minutes of video, this thing recorded a 1.7 GB file."
Recent episodes
All →Showing 80 of 83 products
Clear filtersMentioned in 2 episodes
"This 80% on SweetBench Pro, you'll look at that compared to some of the more recent models that have come out. Very, very good benchmark performance."
"So, it means it follows its instructions. And they're saying that SWEbench Pro, they're hitting 69.2%"
Mentioned in 1 episode
"If you haven't paid attention, this is Anthropic's hosted harness, hosted sandbox for running long running aentic work. I am still trying to figure out what a good use case for cloud manage agents is."
Mentioned in 1 episode
"You can also find this podcast on Apple Podcasts, Spotify, or your favorite podcast app."
Mentioned in 2 episodes
"Look at this Fable 5 compared to Opus 48, GPT55 and Gemini 3.1 Pro."
"They're saying that SWEbench Pro, they're hitting 69.2% which is almost five points higher than Opus 4.7, almost 10 points higher than GPT-5.5, and 15 points higher than Gemini 3.1."
Mentioned in 1 episode
"You can also find this podcast on Apple Podcasts, Spotify, or your favorite podcast app."
Mentioned in 1 episode
"Now, something you'll notice about every time you generate videos and it used to work like this in Veo 2, so I'm not Veo 3 as well."
Mentioned in 4 episodes
"And what's really funny again with the hallucination is you see here, no, I didn't. This is a common thing that I had Opus 4.8 say to me. No, I didn't search Claude."
"Anthropic released something very similar in the Claude API called outcomes. You define what done looks like for an agent, it can self-grade and iterate until it gets there."
"So you have actually named your clouds and then you give them instructions to listen to each other."
"you could actually upload this to like a chat or Claude and you could say explain to me why the photos don't match the mood board"
Mentioned in 2 episodes
"They're saying that SWEbench Pro, they're hitting 69.2% which is almost five points higher than Opus 4.7, almost 10 points higher than GPT-5.5, and 15 points higher than Gemini 3.1."
"Even I do this at ChatGPT, we've created like a Figma page with a bunch of screenshots and they always go out of date."
Mentioned in 10 episodes
"In VS Code in cursor and whatever your IDE is, loading a project at the multi-repo level is really important."
"Multi-person collaboration, multi-player collaboration in a way that prompting code in something like a Codex or a Cursor or Claude Code really isn't built for."
"what percentage of our engineers are using Cursor? Do we have power users?"
"Today's engineers use cursor and claude code to ship features in hours that used to take weeks."
"Today's engineers use Cursor and Claude Code to ship features in hours that used to take weeks"
"OpenAI, Perplexity, and Cursor are already using WorkOS to move faster and meet enterprise demands."
"OpenAI, Perplexity, and Cursor are already using Work OS to move faster and meet enterprise demands."
"OpenAI, Perplexity, and Cursor are already using WorkOS to move faster and meet enterprise demands."
"OpenAI, Perplexity, and Cursor are already using WorkOS to move faster and meet enterprise demands."
"AI innovators like Langchain, Writer, and Cursor scaled faster and closed bigger deals by getting security right early with Vanta."
Mentioned in 2 episodes
"you're getting according to Google's benchmarks a super smart model sort of a Codex 4.7 model if you like 4.7 at the speed of something much more like their 3.1 flash model"
"OpenAI released something in Codex called goal. You can do {slash} goal in beta in Codex and it'll basically bang its head against the problem, do what's called a rough loop"
Mentioned in 1 episode
"when I do hear people talk about anti-gravity, they say it's quite good. Anti-gravity is Google's IDE, Agentic IDE"
Mentioned in 1 episode
"Google AI Studio, Google's sort of low code, no code coding product. Now you can build apps that read sheets, draft Gmails, organize Drive, see your calendar"
Mentioned in 1 episode
"this was 10 seconds long and so it really is much longer than I think the six or seven seconds that Sora was"
Mentioned in 1 episode
"I do not know if these limit increases apply to Claude Design. I suspect they do not, but I hope they will."
Mentioned in 1 episode
"They might put data centers in space. There was a partnership with SpaceX."
Mentioned in 1 episode
"But again, this idea of outcome is define a rubric, give the agent the task, let it bang its head against that at least 20 times till it gets it right. I think this really interesting model for agenda products and something I suspect many of us will use."
Mentioned in 1 episode
"You're basically like duct taping a Raspberry Pi to the back of a keyboard and at night instead of like getting your light on and like scribbling a note"
Mentioned in 1 episode
"There's this quote from the CTO of Ramp that has been one of our leading points, which is no UX is the best UX."
Mentioned in 1 episode
"These prototyping tools, while I think great, you know, the Lovables, the v0s, the Bolts, etc., also have this concept of design system import."
Mentioned in 5 episodes
"These prototyping tools, while I think great, you know, the Lovables, the v0s, the Bolts, etc., also have this concept of design system import."
"Lovable lets you build working apps and websites by simply chatting with AI. Then you can customize it, add automations, and deploy it to a live domain."
"Lovable lets you build working apps and websites by simply chatting with AI. Then you can customize it, add automations, and deploy it to a live domain."
"Lovable lets you build working apps and websites by simply chatting with AI. Then you can customize it, add automations, and deploy it to a live domain."
"This episode is brought to you by Lovable. If you've ever had an idea for an app but didn't know where to start, Lovable is for you. Lovable lets you build working apps and websites by simply chatting with AI."
2 recommended · 37 sponsored · 3 warned against · 286 episodes