/Tech6h ago

Anthropic's Claude Fable 5 Enables Overnight Software Task Delegation

222831744026.5K
Original post
Dan Shipper 📧@danshipper#1462inTech

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

10:28 AM · Jun 10, 2026 · 20K Views
Sentiment

Many users are excited about Anthropic's Claude Fable 5 because its overnight task delegation helps fix code issues, perform migrations, and boost productivity.

Pos
100.0%
Neg
0.0%
6 comments with sentiment.
Cluster Engagement
Posts from X
Most Activity
Most Activity
VIEWS3.8KBOOKMARKS10REPLIES1
Dan Shipper 📧@danshipper

YouTube: https://www.youtube.com/watch?v=XWpTgCvgYaE&feature=youtu.be Spotify: https://open.spotify.com/episode/7s1VcIHp1q6PG9hofb2fVY?si=DsAlKVymRs2-J0cnM25M6w

Dan Shipper 📧@danshipper

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

6hViews 3.8KLikes 7Bookmarks 10
LIKES10RETWEETS2

So many gems from @mikeyk and @danshipper in this one, but especially loved Mike explaining his craziest use case of Fable + dynamic workflows

Dan Shipper 📧@danshipper

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

6hViews 2.8KLikes 10Bookmarks 5
HeyNikhila@HeyNikhila

@danshipper Can Fable change FormNX's CSS framework from Bootstrap to Tailwind CSS?

gonna try it

5hViews 142Bookmarks 1
Patrick Müller@patrickpmller

@HeyNikhila @danshipper Sent even opus on a migration journey from bootstrap to tailwind on an older backoffice on the weekend. It did well with some guidance at the start - so I’d hope fable to work more hands off there.

5hViews 11Likes 1
Ofek Shaked@VibeCoderOfek

@danshipper Benchmark wins that only appear after enabling an undocumented flag inside a 12k line codebase are not the same as reproducible improvements most teams can actually use.

5hViews 70
Julley Thai@julleybuilds

@danshipper day 1 and Fable helped me fix 40 unnoticed code issues

cannot imagine what day 10 will be

6hViews 19Likes 1
Prateek Jain@realprateekjain

@danshipper But what do you guys at every use it on? Are there any products besides the newsletter?

3hViews 17
Element Dong@elementdsj

@danshipper fable is amazing

6hViews 15
Ferbin@Ferbin08

@danshipper Guardrails are the product, not the loop.

Ran a trading bot overnight without them. One error became a full liquidation by 6am.

Setting up a loop is easy. Not blowing up is the hard part.

3hViews 9
Artem Apfelbaum@iamapfelbaum

@tedescau @mikeyk @danshipper full task delegation is the real unlock — ive been leaving agents running overnight since codex, wake up to shit done or shit broken, both teach me something

4hViews 8
HeyNikhila@HeyNikhila

@patrickpmller @danshipper That's good to hear. I will try it

starting the 1st task with complete marketing pages analysis

5hViews 7
Rich@RrichPRMR

@danshipper The recruiter quote is one of the strongest descriptions of AI I’ve heard

6hViews 3
dien sharif@diensharif_

@danshipper ran my stack overnight like this and the unlock wasnt the model, it was making the task verifiable before walking away. a loose spec just loops confidently in the wrong direction for six hours. tight scope plus checkpoints beats raw model strength every time.

5hViews 2
Mike B@Mike_nike7

@danshipper The unlock in agentic loops isn't compute — it's learning to trust the output without watching every step. That shift takes longer than the technical setup.

3hViews 1
Bruchez@thebruchez

@danshipper Maximizing ambition with Claude Fable 5 sounds exciting, especially with its task delegation capabilities. What kinds of projects are you planning to run through it?

5h
LeBonPrompt@LeBonPrompt

@danshipper Reviewing work you never watched get built is a skill nobody trained for. That's the part that'll bite teams hardest.

6h