Wasn't happy with the results I was getting from Claude just now so I looked at the model selector and realized it was set to Opus 4.7 for s...

It's been a minute since I read an S-1, but you can bet I will be reading this one! https://twitter.com/AnthropicAI/status/21147050428171102...

I can't believe we live in a world where I can just say "go read this canonical @every piece to see how it tackled it" and AI can just do th...

I'm deliberately keeping my Bible app low-AI for now because I want to make sure it's *my* observations and syntheses going into it But a v...

A fun thing about a shared company agent if you're neurotic, like me, is that you can ask it to give you a performance review any time you w...

I love that “watching someone play StarCraft” is a legitimate way to investigate AI behavior. Games ftw. Great piece by @alxai_ in @every...

A thing I'm noticing about my prompting is that I often start "If you were going to..." or "If asked you to.." There is no "if." It's happ...

I've been on the fence about personal agents, but with @every Thesis and my birthday coming up, plus a speaking commitment, plus a couple of...

New benefit AI-forward companies should offer: personal AI stipends to cover employees' personal agent use.

Re-upping this on main: I've been working in a Google doc in Claude's in-app browser all day and giving edits to agents to execute as sugges...

Just maxxed out my Fable usage for the first time, am simultaneously very proud and very sad

It only took about five different spec versions, a bake-off between five different frontier agents, and a couple hours of hands-on fiddling,...

Codex is the kind of product that deserves a definitive history, and @danshipper's written it! As someone who was personally Codex-pilled...

This was a heck of a take to come across while procrastinating on an essay for the @every newsletter. It’s not news to me though, nor am I ...

I'm working on a draft, and I wasn't happy with how it was coming together on a sentence level in ChatGPT, so I scooted on over to Antigravi...

Preliminary spot check on the writing quality of Muse Wonder for @every: readability is clocking in at a respectable 8th grade, compared wit...

Every couple of years, tech reinvents content marketing from first principles. I've been around long enough to go through several cycles of ...

We built @Every Agent to work the way Every works, and that includes how we write. Every Agent comes with all 32 skills from Compound Writ...

A very analog Bible study whilst the latest batch of frontier models take their stab at building me my dream Bible study app.

I'm a simple person: I see new a writing model, I test that new writing model. My initial read on Echo is that it's in a similar place to ...