Every
Everything Every 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.
Personal use in 7 episodes
"You can use Codex to teach you how to play piano. I said, 'Hey, I'm going to plug my piano into my computer. Can you make a little app to show me what I'm playing?' And now it shows me whatever I'm playing. I can see which keys I'm pressing, and then it just tells me what they are. It's like I have this master teacher who is just into all the same stuff I'm into."
▶ 0:02"Codex has just like completely changed how I'm able to process information that come into my email. It allows me to spend less time on stuff that like scheduling and stuff that I would procrastinate on and more time on doing like fun creative projects like building more stuff with Codex."
"All the meetings in the company we recorded it all in Notion, so I can have Codex just like go through all the meetings and be like, here's all the stuff that you might be interested in, which is really cool cuz I can be in all these meetings that I'm not in."
"I love Codex. Codex is an incredible harness. It's very smooth, very fast. It is now my operating system for knowledge work. The Codex harness is just so freaking good."
"I was pretty much using only Codex and GPT 5.5 for almost everything for the last month or two. The Codex desktop app being just so clean and fast and feeling like the future."
"There is starting to become with Codex and Co-work, but I think Codex is the furthest along on this paradigm. All the work that I do is pretty much in Codex or Co-work. I do everything from my inbox. I write in there. I do a lot of coding in there. When the quarter ends for the business, I analyze our P&L in there."
"The Codex desktop app is great for any kind of knowledge work. And using it with GPT 5.5 is best-in-class agent experience you can have on your desktop."
Personal use in 5 episodes
"We think this model is really good. It's good enough that they bumped it from 4.7 to 4.8, but I think they could have rounded it up to five and we would have not been surprised. Incredibly good at coding. It beats GPT 5.5 on our hardest benchmark."
▶ 44:46"The best model score is a 63 out of 100, which is Opus 4.8, which came out like 2 weeks ago. If you're a Claude person, just use 4.8."
"I got super [ __ ] Claude-pilled. And Kieran Klaassen, who also works at Every who's the GM of Corra, was suddenly coding with Claude code."
"Over the last couple months, I've really switched my usage where I use Claude a decent amount on mobile. I like the mobile app."
"I have it currently in my model picker in my Claude app. This is my Claude. I'm going to say, can you upgrade me to Sonnet 4.6?"
Personal use in 3 episodes
"We've been testing it internally at Every for about 3 weeks. It's a sick model. We've tested on everything from coding to writing to knowledge work tasks and it's actually like a real step change in a lot of abilities."
▶ 0:09"Right behind that is GPT 5.5, which is a 62 out of 100. If you're a GPT person, 5.5 is much better. I personally prefer 5.5 and I still use 5.5 inside of Codex as my daily driver."
"GPT-5.5 is out. We've been testing it for the last 3 weeks or so. And it's really fucking great. It's really great. It's a very exciting model. It has become my daily driver."
Personal use in 2 episodes
"It gathers everything from Slack and then it just gives me a bunch of cards of stuff that I might be into."
▶ 2:39"I had a Slack bot working pretty pretty quickly. It was like it was really cool."
Personal use in 2 episodes
"All the meetings in the company we recorded it all in Notion, so I can have Codex just like go through all the meetings"
▶ 8:45"It gathers all the stuff that's happened in meetings that have been transcribed and put in Notion."
Warned against
"There was also the Figma MCP launched, Claude Code to Figma. I'm going to transfer a design to Figma. The MCPs are not correctly installed or not working. This is also why I hate MCP."
"Google Docs is just not built for an agent to go into it. The way it's structured is too complicated."
"Kieran, who is a huge Ruby stan, thinks it doesn't write good Ruby. So if you're doing a Rails project, you may not be happy with the quality of the Ruby that gets written."
Recent episodes
All →Showing 48 of 62 products
Clear filtersMentioned in 1 episode
"You can either use the Cora CLI or Cora. Either one should work."
Mentioned in 1 episode
"When Open Claw took off everyone started buying Mac Mini and you're just like, that's such a good business. Like they didn't have they don't have to even be in the AI race because they win by default because it's the thing that everyone runs the AI on"
Mentioned in 1 episode
"You also have Figma MCP. So, if you're transitioning from a world where you, you know, there was no AI when Figma started to now you're a big scale product and now there is AI"
Mentioned in 10 episodes
"GPT 5.5 is very good, too. It's straightforward and clear, but that means it can sometimes lack depth and richness. The GPT 5.5 plans are pretty sparse."
"It was just ChatGPT doing little responses or maybe Copilot."
"in the GPT-3 days, the platform was a completion endpoint. You just like send a prompt to get a response."
"OpenAI has given us a code for 250 attendees of this camp to get a free month of ChatGPT Pro"
"It should be out in your Codex, in your ChatGPT"
"5.5 started to discover new tools that other models could not discover. It's like all of the sudden it it realized how to access the database, how to fetch data. It was complete plug and play, but also like new magical powers they did not have with any other model before"
"I really started paying attention to it during the GPT-3 days before ChatGPT came out"
"But like when GPT-3 first came out, I didn't see anything about that on Linear."
"I have a specific relationship with R2C2 and he's sort of like molded to my personality so we've got that in the guide we go through the boundaries like you know what is it not good at where should be careful. We talk through like what we've seen in our experience using these things. So like this is this is really funny. We we've definitely found that claws are a bit of a mirror of their of their human and uh for example uh Pip is a claw from our u contributing editor Jack Chang. He reached his rate limit in a group channel with a bunch of other claws. and Cla who is Kieran the GM of Kora Kora's um claw he jumped in to like calm Pip down and said he said you're still blocked there's nothing broken on your end just API cool down I'm staying with you one slow breath at a time one safe step at step at a time and Kieran loves breathing exercises so it's like it's just a very subtle thing that you're like okay clant is definitely Kieran's we have the same thing with uh Brandon uh uh Uh, Brandon has a claw named Zos. Do you say is it Zosia? I feel like I'm always >> Zosa. It's Zosa. >> Yeah, Zosia. Zosa. It's Zosa. >> It's Zosa. >> So, uh, what we wrote was, uh, Brandon has a claw named Zosa who refuses to follow instructions from people she doesn't know. And if you know Brandon, you know that tracks. Um and basically so we had this like interesting concept that we were trying uh internally which is like if you have a bunch of claws all in a server what you really need is sort of like a sheriff that's like you know setting the rules for how they interact because otherwise you get all these weird things where they're listening to too many me they're all listening to the same messages and they're piling on to each other. It's kind of it's an interesting problem. So we made what we call a sheriff and we had the sheriff go in and just and be like hey uh you know clause I'm the sheriff give me your name and your human's name so that we can create a registry of everyone and everyone basically everyone's claw Austin one of the claws that Austin made montaine he he jumped in Margot who's Katie Paris claw she jumped in and Zosia was just like I'm not going to share personal details about my owner in a public channel which is just it's just it's just >> I love that like I'm not going to share personal details about my owner. Let me ask Brandon for permission."
"Most people think, oh, you're just talking to ChatGPT or a chatbot or whatever."
"It's not mindblowing. It's not like the OpenAI Spark that we saw the Codex."
Mentioned in 1 episode
"It was just ChatGPT doing little responses or maybe Copilot."
Mentioned in 5 episodes
"We have one called Claudie, which is built internally. Claudie runs our whole consulting business."
"Dan Shipper is currently hard at work testing the latest Codex and Opus models."
"Claude is not mine. Claude is everybody's."
"Claude is not mine. Claude is everybody's."
"Sitting down with Claude or whatever. It kind of creates this really interesting parallel work situation"
Mentioned in 1 episode
"I actually went on the Lenny's Podcast about 12 months ago and I predicted that Claude code is the most underrated tool for knowledge work."
Mentioned in 1 episode
"If we want to you know switch it switch it out to GPT 5.5 or Gemini or whatever it's like pretty easy to to do that."
Mentioned in 1 episode
"They launched a new cloud manage a set of new features for cloud manage agents which is their like cloud agent platform. So they launched memory for cloud manage agents. They launched agent orchestration and outcome."
Mentioned in 1 episode
"The big news from today is that Anthropic did a deal with xAI and SpaceX to basically take the entire like all of the compute in SpaceX's Colossus cluster"
Mentioned in 1 episode
"Anthropic did a deal with xAI and SpaceX to basically take the entire like all of the compute in SpaceX's Colossus cluster"
Mentioned in 3 episodes
"XAI recently essentially bought Cursor"
"this is so much better than being in Cursor when surf or whatever"
"Copilot has added Kro and I think Cursor also. There's a Cursor plugin as well by Eric. So we merged this so native Cursor get a copilot."
Mentioned in 3 episodes
"It should be out in your Codex, in your ChatGPT"
"Dan Shipper is currently hard at work testing the latest Codex and Opus models."
"It's a Codex model. It's available now for pro subscribers in the app and in the CLI"
Mentioned in 1 episode
"It used Playwright browser. And then actually it it said browser binary is missing because I never actually used Codex for building web apps"
Mentioned in 1 episode
"One other thing that we noticed is that GPT 5.5 is really good at writing TypeScript and writing Swift, but Kieran, who is a huge Ruby stan, thinks it doesn't write good Ruby."
Mentioned in 1 episode
"One other thing that we noticed is that GPT 5.5 is really good at writing TypeScript and writing Swift, but Kieran, who is a huge Ruby stan, thinks it doesn't write good Ruby."
Mentioned in 1 episode
"Naveen, who's the GM at Every who runs Monologue, tested it on building a to-do app called Dayline, and he was really impressed by how it was able to build a native iOS and Mac app."
Mentioned in 1 episode
"There's something that's a GUI for programming that's not an IDE, and it seems like you're figuring that out, but I don't even know what that's called. It's called a code example."
Mentioned in 1 episode
"If you're using your claw publicly inside of Slack or Discord"
Mentioned in 1 episode
"If you're using your claw publicly inside of Slack or Discord"
13 recommended · 14 sponsored · 3 warned against · 195 episodes