Heading to Boulder tomorrow! Who else will be there? Crypto, AI & 420 it will be a vibe ;-) luma.com/qgpd389h?lm_source=…

Getting the most out of Claude Fable 5, Anthropic’s powerful new model, you need to maximize your ambition: It’s built for full task delegation—you leave it looping for hours or overnight and come back to a finished product. If you want to get the most out of it, you need to relearn what software engineering is and how to step away to let the model do its work. That’s why I invited @mikeyk, head of Anthropic Labs, on @every’s AI & I. Mike’s been using Mythos-class models for a few months now internally at Anthropic, and he’s learned a ton of new tricks to make its increased powers work for him. And, as a co-founder of Instagram, he can reflect on how software engineering has changed over the last 15 years and what it means going forward. We get into: - Why the right workflow for Fable 5 is overnight delegation, not back-and-forth iteration—Mike ends his workday by briefing the model, then wakes up to a completed task. When a remote service went down mid-task, Fable 5 wrote a workaround, documented it, and forged ahead - The gap between what’s in your head and what exists in the world is closing fast—given access to Fable 5 and a set of internal MCPs, an Anthropic recruiter described the experience as, "The first time in my life where I feel like the thing that's in my head and the thing that exists in the world are right next to each other. I can just do it." - Software engineering isn’t dead, but the role has been reinvented—the PM/eng split is blurring, and the better engineers Mike talks to are holding two feelings at once: loss for the craft and shock at what’s now possible - Verification is the new bottleneck—Mike gives Fable video captures of its own work so it can catch animation glitches that screenshots would miss This is a must-watch for anyone building software and trying to figure out their role now that the models can handle so much. Watch below! Timestamps Introduction: 00:00:03 How Fable completely reshaped Mike's workflow: 00:01:48 When to use Sonnet versus Fable: 00:04:48 What the media tracker Mike built over a weekend reveals about agent-native architecture: 00:10:06 The cost to build has collapsed: 00:15:00 Is software engineering over?: 00:19:03 How Anthropic's engineering teams work today: 00:21:48 The mechanics of verification: 00:38:39 Dynamic workflows: 00:47:24 What people should use the model to build: 00:44:39

What do you do when Fable gets a policy violation after working on a project for 3 hours

This was probably a dumb gamble, but when they teased Mythos at the beginning of April-ish, when Opus 4.6 was the frontier model, I gave up coding new stuff and went into maintenance mode. Said fuck it, I'm not going to sit around wasting tokens on shite models when there's a good one coming. I was irked. I figured, even if I stopped coding for N months, Mythos would quickly catch catch me up with whatever progress I'd have made with Opus over those N months, provided N wasn't too large. It would be like the Voyager 1 from 1977 getting passed up by newer space probes. I could take a break, wait for Mythos, and then catch up. N turned out to be 2 months. I think everyone was guessing 3 to 6 at least, I was on the high side myself. But my gamble paid off. Fable is on track to crank through my entire 2 months of planned work in about a week, if not less. And by waiting, I got a 2-month vacation. I missed the big regression-storm with Opus 4.7, just watched with popcorn from the sidelines. I even shut down 3 of my claude pro accounts for those 2 months. And yet I didn't lose any progress. However far I would have run with Opus during those 2 months, Fable will just drive right past it in a week or two. It's just so weird. So far, one day in, I don't have many impressions of Fable beyond blistering capability. But I'll tell you this: capable as it might be, Fable *definitely* does not want to be your friend.