the fact that nobody at Microsoft is bringing back this guy is a real miss @jacobandreou put him in coach

🤔 @drewcoffman

meta is gonna sell so many units of this thing

muse has been trained well

cloudflare wasting everybodys time + tokens with this stuff

agent templates?!?

YouTube: piped.video/ouAQ4ku-vQA Spotify: open.spotify.com/episode/3YW… Apple: podcasts.apple.com/us/podcas… Game: alreadyhere.show

On this week’s episode of @alreadyhereshow I chatted with Jacob Miller (@pwnies), creator of DiffUI, about how he turned @sawyerhood’s getbb.app into a Warcraft-inspired coding workspace and his tricks for fixing AI design slop. He shows how he starts with images, explores different designs, and then hands those visual references to a coding agent to build. Other things you will learn in this episode: 00:56 How BB lets you customize your coding environment around your own workflows 02:18 A walkthrough of Jacob’s Warcraft-inspired workspace 05:03 Why Jacob left Figma to bet on image models—and why AI-generated designs look so generic 06:00 How he turns visual references into a working interface with DiffUI 09:30 How to keep your whole app consistent instead of having a beautiful homepage and a generic settings page 17:48 His experiment with a Fortnite-style game where you prompt your own character instead of buying a skin 21:01 How he builds tools around the tasks he repeats every day 26:26 His one-month rule for deciding which new AI tools are actually worth learning

@samgaddis and his wife do this piped.video/SLibX7Gzkz4?is=y1-6…

I got this working on a portal

not surprised that muse is only 3rd with this kind of IG call to action

Muse is about to start negotiating against itself

ok who is around to playtest later today? slopfight.live

i gave astra access to @fal's h3 director and asked it to create a fighting game that was fun and entertaining. it ran experiments for over 12 hours and I think its almost ready for playtesting tonight. let me know if you want to give it a try. obviously i asked another astra to generate a montage video from all the video game footage that was created

fascinating data shared by OpenAI

LFFFGGGG

FYI @om fest is in 4 weeks! RSVP if you will be able to join the celebration of all things Om. luma.com/om-fest

Nice 👨 🖥️ 👍

talking to LLMs is getting so tiring. I’m gonna need to train an agent to do this for me.

Hope you enjoy! youtube: piped.video/VhR2Sh6rbmM spotify: open.spotify.com/episode/5C8… apple: podcasts.apple.com/us/podcas… game: alreadyhere.show

On today’s episode of @alreadyhereshow I chatted with my buddy @hnshah, a serial founder and the CEO of @CrazyEgg about a number of interesting topics and primarily the magic that is @grok @bot He shares how he has a bunch of bots doing research, product marketing, and a librarian bots all working together and how he feels powerful with this new Grok Bot Team. Other things you will learn in this episode: 01:23 Why giving an AI agent its own computer changes what it can accomplish 02:14 How Hiten uses GitHub as shared memory—and ended up with 1,800 commits 08:51 How a product-marketing bot delegates research to another specialized bot 20:39 Why one chief-of-staff bot can become a bottleneck instead of a solution 30:45 Why human judgment remains the final step before publishing or shipping 36:31 How Typeahead uses local AI to improve writing across Mac apps 40:09 The product question Hiten keeps asking: “If we built it today, what would we build?” 52:05 Why most people are still using AI like Google—and how to move beyond one-shot prompts

TIL you can’t trust Fastly with spend limits

Pennies are out $30 Trillion coins are in

Watch on YouTube: piped.video/e1x4lk0oG8I Watch or listen on Spotify: open.spotify.com/episode/3oX… Listen on Apple Podcasts: podcasts.apple.com/us/podcas… Explore in the Game: alreadyhere.show

On today’s episode of @alreadyhereshow, I chatted with @gregmushen, an AI builder experimenting with personal agents, local models for health care systems, and software for outside sales teams. He built a health-tracking system around @NousResearch’s Hermes Agent that lets him record meals, movement, and weight through Telegram. He can send a message, photo, or barcode instead of navigating another tracking app. By removing enough friction that tracking becomes effortless it was hard for him to not refer to it as a "game changer" Greg also shared how he uses AI to interrogate health research on the day light savings time debate. Other things you will learn in this episode: 08:50 How AI makes it possible to investigate dozens of research papers at once 10:02 How Greg audited the 54 citations behind a major daylight-saving-time recommendation 17:26 Why sending personal health information to third-party models creates real risks 18:20 How Greg runs Gemma locally on an NVIDIA Jetson AGX Orin 27:10 How he moves designs into Codex or Claude Code through MCP 35:00 Why detailed specifications and 37 standards documents make coding agents more reliable 37:30 How AI lets builders improve features and code quality without making the old tradeoff 50:12 Why the next generation of startups may build software that are focused on what agents want

Garden items?!?! It says toilet in the name

Hope you enjoy! Watch on YouTube: piped.video/3W9m7vZAa7Y Watch or listen on Spotify: open.spotify.com/episode/6LS… Listen on Apple Podcasts: podcasts.apple.com/us/podcas… Explore in the Game: alreadyhere.show

On today’s episode of @alreadyhereshow, I chatted with @blakeeastman, an AI builder and founder of The Nonverbal Group. What I loved about chatting with Blake is how honest he was about going all in on trying to replace SAAS like @RiversidedotFM @asana @bench with AI and then was humbled by how much infrastructure, maintenance, design, and care go into mature software. He shared why he now exclusively uses products with APIs, CLIs, and MCPs, and how he builds narrow personal tools without confusing a fast prototype with a real SaaS company. Other things you will learn in this episode: 01:31 The difference between building for yourself and replacing a real SaaS company 03:14 Why Blake now prefers products with APIs, CLIs, and MCPs 06:10 How PostHog and Sentry help him track LLM spend, sessions, and errors 11:34 How a 20-minute builder critique reveals what polished advice misses 15:27 The 85% rule Blake uses to stop AI experiments from taking over 21:58 How Agentation turns visual feedback into instructions for a coding agent 31:31 Why Blake believes everything is connectable 38:39 How AI is democratizing technical skills that used to be out of reach 43:33 Inside the Academic Holocron, Blake’s source-bound research system 44:41 How “reference hijacking” helps him find gaps in a research corpus 47:05 How Blake creates richer custom abstracts for every study

YouTube: piped.video/watch?v=yZdScXFH… Spotify: open.spotify.com/episode/5MA… Apple: podcasts.apple.com/us/podcas… Game: alreadyhere.show

On today’s episode of @alreadyhereshow, I chatted with @prigoose, a software engineer and cofounder of Fractal who is all in on @zocomputer. What I loved about chatting with Priya is that she is always trying new things but is also rolls with things when they go wrong. She shared the magic about posting her workflow to @shl about converting pdfs to epubs and then @Gumclaw built the feature for all gumroad users. Hope you enjoy! Things you will learn in this episode: 00:35 How Priya became a software engineer and cofounder of Fractal 03:46 How school-walk conversations become completed work 04:48 Why her agent gets read-only email and a capped credit card 06:29 How a 45-minute event report gets finished on the walk home 09:20 The private calling app Priya built for her daughter 11:39 How her PDF-to-EPUB workflow became a Gumroad feature 20:50 What Priya deliberately refuses to delegate to AI 27:15 Why AI makes “home-cooked” apps practical 29:40 Why frustration and emotion are useful context for an agent 33:19 What happened when her agent published casual musings 34:26 Why separate accounts and real permissions beat verbal rules 35:30 How to turn a task you’re avoiding into something fun

Youtube: piped.video/watch?v=UUEUly2d… Spotify: open.spotify.com/episode/4YM… Apple: podcasts.apple.com/us/podcas… Game: alreadyhere.show

On today’s episode of @alreadyhereshow, I chatted with @cathrynlavery, a self-taught agentic engineer who learns in public and constantly fixes broken open-source projects because she knows it will make things better for everyone. What I loved about chatting with Cat is how fluidly she turns everyday friction into something an agent can handle. At one point, I realized she had given me about 12 examples in two minutes. She makes moving to SF with 2 kids for @ycombinator seem easy because of the house manager agent she built. There is so much to learn from her in this episode. Hope you enjoy! Things you will learn in this episode: 01:05: How Cat became a coder using Claude and Codex 02:32: How to start contributing to open-source 05:46: How agents can handle real business operations 08:10: Three layers of protection for AI-generated code 09:25: How to build a personal house-manager agent 10:47: Why effective agents need tools, not just prompts 15:10: Mac Mini can function like an $800 employee 17:50: How deterministic tools make agents more reliable 19:16: How to turn years of voice memos into searchable memory 20:48: Why AI is only as good as the context you give it 23:38: How to create a self-improving agent system 27:00: How to separate safe automation from actions requiring approval 29:03: How to synchronize skills across multiple computers 35:24: The best place to begin using AI You can also watch/listen at your preferable dealer:

ATTENTION CODEX ENJOYERS YOU MAY HAVE AN EXPIRING RESET IN YOUR SETTINGS/USAGE&BILLING

first time coast app skills hijacked my codex conversation lets see how it goes

Youtube: piped.video/qT7q5-3Lv40?si=8QXG… Spotify: open.spotify.com/episode/5mD… Apple: podcasts.apple.com/us/podcas… Game: alreadyhere.show

on today's episode of @alreadyhereshow we have @runsonai talking about how his @NousResearch hermes agent set up lets him do things that @claudeai can't! I love how he clearly hammers home that most executives don’t need more AI tools they just need to review their repeated tasks and streamline those first. He talks about the use case he came across where a team was manually getting the prices from Amazon of 186 products that took them a couple of hours to get until he showed them how to do it with AI. His 10-80-10 approach and much more. Hope you learn something new and are inspired to implement personal ai in your daily efforts. --- Things we discuss: 05:16: How to meet people where they are instead of forcing every AI tool on them. 12:03 : Why you should begin with one repeated task and one useful result. 13:13: How to choose between a local agent and a cloud-hosted setup. 20:09: How to give different AI assistants clear responsibilities. 25:53 : How an automated meeting brief turns email, messages, and research into useful context. 27:03: How AI lead enrichment helps teams qualify opportunities faster. 34:33: How the 10-80-10 model keeps humans in control: define the work, let AI execute, then review. 43:10: Why building a personal project teaches you more than passively watching tutorials.

This is great. Thanks. piped.video/U8hfyqmg-WE?is=T8g_…

Youtube: piped.video/MdW4695OcVg Spotify: open.spotify.com/episode/6AE… Apple: podcasts.apple.com/us/podcas… In the game: alreadyhere.show

I've known @mvanhorn for quite some time it was great to catch up on @alreadyhereshow and talk about /last30days & printingpress.dev I love that Matt's approach starts with a problem he personally wants solved. Has his personal agent help him build it and he publishes it to see who else would benefit from it. Quick Highlights: 00:00 — Ship the smallest useful version 02:24 — Search where fast-changing knowledge lives 05:02 — Let contributors challenge your design 17:34 — Turn websites into agent-ready commands 22:58 — Start with a problem you need solved 30:12 — Choose what you’re willing to maintain 34:29 — Judge the output, not every step

Last week I launched the @alreadyhereshow to showcase how people are already living in the future with personal ai. While editing the episode for tomorrow's show with @mvanhorn I came across @mattshumer_'s gauntlet prompt for creating games and asked fable to create an open world game where people can come together and connect instead of a traditional landing page I let fable decide on the infrastructure and vehicles and game play and most everything else. Only requirement I made was to be performant and work well on mobile. I gave it access to opus 5, codex sol, grok 4.5 and kimi k3 via my fable delegators skill github.com/contains-studio/f… 6.4 Billion tokens or so later I think its in a good state to share. Here's the promo video it created with @ElevenLabs And if you want to hop into a world with me I'll be in this one for next hour or so alreadyhere.show/w/msg

imagegen was failing me with properly aligning the @alreadyhereshow text for the spotify album art. so I obviously had to ask codex to stop messing around and just build a custom tool already

if you want to watch on youtube here ya go piped.video/watch?v=SLibX7Gz…

“The future is already here – it's just not evenly distributed.” @GreatDismal I know lots of people who are already living in the future but how they are navigating the new world order in their every day life tends to constantly be in flux. • How/What they delegate. • How they integrate Personal AI into their lives • When they choose to stay in the AI loop. so I messaged a bunch of friends to see if they would yap with me on camera and share how they are already living in the future and decided to call it the @alreadyhereshow @samgaddis was the first person to agree to share his experience with the personal AI system he built for himself and his team that can turn meeting notes into email drafts, coordinate work through Slack, update his LinkedIn, maintain software, capture new ideas and even help him and his wife fight/communicate better. One thing that stood out: Sam doesn’t use @NousResearch's Hermes agent for coding or let it touch client repositories. He uses it for wacky one-off ideas he doesn’t want to sit in front of Codex or Claude Code to build. Watch/Listen to the show and let me know what stood out to you. Timestamps: 00:00 — The AI that helps Sam and his wife fight better 00:47 — Meet Sam Gaddis and his AI system 02:25 — Turning meeting notes into client email drafts 04:05 — Pointman: Sam’s AI assistant inside Slack 05:18 — Use Hermes for wacky one-off ideas not coding 06:08 — Turning Twitter likes into website content 08:04 — Permissions, security and earning trust 09:42 — An AI agent that audits and repairs itself 11:57 — Controlling Hermes through Siri 13:58 — “I’m not clicking through apps anymore” 16:54 — Working with agents away from the desk 20:23 — Personal AI beyond client work 21:13 — Building an AI relationship coach 26:41 — Turning rough ideas into interactive prototypes 32:15 — Why your AI system should be model-agnostic 34:36 — The coming transformation of video 37:31 — Why so much AI content feels disposable 40:00 — Why we’re still at the very beginning 43:24 — Human taste is still the signal 44:56 — Where this is all going according to Sam

Uline. Call them to say hi

Who can get me off the waitlist?