Adam Kazwell

@zachcoelius curious what countries did this well (and what did they do?)

Imagine if after Covid the federal government had built the infrastructure to protect us from the next pandemic. Craziness.

it’s in gemini, just create it in ai studio. oh, that’s for your personal google one account. for workspace you need gemini business. no, not gemini advanced, that’s ai pro now. unless you need ai ultra. oh agents? you do that in spark actually. no, not gemini api managed agents, that’s different. for coding use jules. unless you mean the agentic ide, that’s antigravity. no, that’s the old antigravity, download the new one. actually gemini cli is being deprecated, use antigravity cli. no the flash model is smarter than the pro model. unless you need pro. if it’s video, use flow. no, flow uses veo. no, nano banana is images. actually that’s in gemini now. unless you’re in search, then it’s ai mode. no, research is notebooklm. anyway it’s all very simple.

@TechWithLucy thanks for using Cuey!! let me know if you have any feedback

I’ve been using Cuey for weeks now, and it’s a been gamechanger 😁 Cuey is a Chrome extension that works inside ChatGPT, Claude, and Gemini. It quietly checks other models in the background and surfaces a stronger answer when one exists. This means no tab switching, no more entering the same prompts again & again. My favourite feature is their “melded answer”. Instead of reading three separate responses, Cuey shows you exactly where models agree, where they differ, and what each one said. It also has a portable memory layer, so your context follows you across tools. 🔗 Try it FREE now: cuey.io Use LUCY60 for 60 days of Pro, no credit card needed. Let me know what you think!

ChatGPT, Claude & Gemini 𝘢𝘭𝘭 give different answers to the same prompt. Most people just trust the first output 🤨 The workaround? Copy the same prompt into multiple tools & compare them. However… it’s slow, manual, and breaks your flow. ⬇️ That’s exactly what @cueyofficial fixes...

@skirano Any tips for handling zooming? With magicpath in codex, when I go to zoom it sometimes just zooms codex, making magicpath UI elements huge 😭

For extra coziness, I recommend collapsing our chat and resizing the Codex one, it literally looks like an entire new app.

You can now run MagicPath as a native canvas inside Codex to design and build functional apps. It's pretty incredible. Here's how to do it 👇

@dshan Google Home Hub, Amazon Kindle (whole lotta Amazon products on this list)

Does anybody with UX experience work on these products? Siri Alexa Amazon Prime Video Wyze Quickbooks Chase (or any bank that isn't Mercury)

@lennysan and also: "sharing the same definition of success" is critical. The struggle to define work you didn’t even realize was in progress has been challenging. x.com/shreyas/status…

Even more broadly, something I'm hearing a lot of: with everyone doing everyone else's job, it's hard to know what your job is anymore.

@henrl @rexsalisbury that is one heck of a "oh, I forget to mention" given your opening statement 😂

@rexsalisbury Yes, waited weeks for a good window and had friends on a boat spotting me!

Nothing is stopping you from buying a board from Costco and paddling to treasure island. Only takes half an hour!

@lennysan @tfadell What’s a piece of particularly tough feedback Steve Jobs gave you that you initially resisted, but later realized led to a meaningfully better product?

The legend @tfadell is coming on my pod soon. What would you love to hear from him?

@TechEmails No way @sama wrote this text. Too many capital letters.

Sam Altman texts Elon Musk October 1, 2020

@tunguz Would love to read … could you Dm or email me? (Last name at gmail)

I am discovering that when you are still in the *very* early stages of your startup, it’s *extremely* valuable to have a well-thought-out manifesto written and available, where you dish out not only the problems that you are trying to work on, but also your general work philosophy. That way when someone wants to “jump on a quick call” you can send them to read it first. This is a great filtering mechanism that eliminates 99%+ of all grifters and NPCs.

@metapreston Agree…in my mind “team” was “people beyond the founder(s)”

@kaz will be very common but not sure its better. a co-founder brings qualities that transcend code generation

The ideal path to VC funding: Idea -> Demo -> Team -> Product -> Traction -> Raise Most will do this out of order.

TIL: Granola has lots of great recipes like this one (and others from @lennysan @nikitabier)

@metapreston chatgpt is a great product name like starbucks is a great company name..... they're both popular despite, not because of, their terrible names.

Anthropic has a good company name and poor product name OpenAI has a poor company name and great product name

@bentossell so damn cool! (but also has to be devastating for Superhuman / other tools that seemed out of reach...looks in Evernote's direction)

@kaz was literally a couple hours work

People joke “nobody’s going to vibe code their own Salesforce,” but it’s been surprising in the best way to see just how much people can now build for themselves. Ben built his own version of Superhuman. I built my own podcast player. I'd assumed both projects would be "too big" to vibe code, but nope!

@pandemona "Podcasts are the largest source of untapped data on the internet" is such a powerful statement. Been true for over a decade. Wish you luck in tapping into that data.

Podcasts are the largest source of untapped data on the internet. But searching audio is still broken. Today, we're launching a product to fix that. Meet the Particle Podcast Intelligence API. Track mentions or topics, get shareable clips, uncover ad intelligence, and get access to rich metadata. Tell your agent: "Go to docs.particle.pro" 🛠️

@zachklein “sharing the same definition of success” nails it. The struggle to define things you didn’t even realize were in progress has been challenging.

@kaz Obviously there are a bunch of contingencies, like sharing the same definition of success.

There are two kinds of people after dinner: Those who ask, “Can I help?” And those who are already doing the dishes. One sounds helpful. One is. This plays out on every team every day. Don't wait for permission. Do the dishes.

This reading hack always seemed to work, but it was never worth paying/subscribing to a tool that offered it. rapidreading.lovable.app