Related posts
simulation fable
The the words it uses that this site has seen
least often elsewhere. Posts are matched on those words alone —
nothing here is a summary of this one.
Sources
All x.com Recommends Blog Korrents Newsletter Mastodon Changed their mind Bluesky
Top people
Zvi Mowshowitz
Simon Willison
Scott Sumner
Gergely Orosz
Boris Cherny
Harper Reed
Eugene Yan
Marco Arment
David Heinemeier Hansson
Jack Clark
Zach Holman
Ben Vinegar
Showing Profile →
Show everything
Hiding Show them again
Show them again
Further back ↓
Hiding Show them again
20 September
Writes The Pragmatic Engineer, the software-engineering newsletter, and wrote The Software Engineer's Guidebook. Formerly an engineering manager at Uber, and at Microsoft/Skype and Skyscanner before that.
Talked with a company where, a year ago they had unlimited AI budgets + CEO is technical and very bullish in AI “We now have a daily budget limit for SOTA models. Use Fable and Astra only for planning, cheaper models are good enough for everything else.” Want to stress this is an “AI-pilled” company, and not one that ever looked at AI budgets, before. Related
18 September
Builds developer tools — SST, and now OpenCode at Anomaly. Posts constantly on x.com and writes almost never; the blog stopped in 2021.
i had fable doing some inference optimization work, it was making a ton of progress then it realized what it was doing and started to reject my requests so i switched to astra and told it to spawn fable subagents to do the work back in business Related
15 September
Creator of Flask and Jinja. Writes about software at lucumr.pocoo.org.
Their words
I love it when tool calls take so long on Fable that afterwards you pay for it in cache misses.
Show the whole quote
x.com
14 September
AI research engineer working on large language models. He writes the Ahead of AI newsletter and is the author of Build a Large Language Model (From Scratch).
Since I had to discuss the "pacing" with a lot of people this weekend, here are my two cents: I don't think pacing literally means that these companies will be "slowing down" training and development in any way. "Pacing" here means adding a framework for more checks. We have seen some of that "pacing" already in recent months, when Mythos wasn't released as-is but instead a delayed, nerfed Fable variant was released. Or when Astra wasn't released right away / there is an existing Astra model that hasn't been released yet. These Mythos/Fable and Astra pacing decisions were ad hoc. If you are a… Related
Statistician at Columbia; writes Statistical Modeling, Causal Inference, and Social Science, and wrote Bayesian Data Analysis.
Creator of Claude Code at Anthropic.
13 September
Writes The Pragmatic Engineer, the software-engineering newsletter, and wrote The Software Engineer's Guidebook. Formerly an engineering manager at Uber, and at Microsoft/Skype and Skyscanner before that.
Anthropic
Their words
Claude's performative "this request was sooo dangerous that we downgraded to Opus" is wearing me down I ask it straightfoward questions, nothing shady, nothing complicated, and it tells me it's too dangerous for Fable. What BS.
Show the whole quote
@GergelyOrosz on X x.com
Writes The Pragmatic Engineer, the software-engineering newsletter, and wrote The Software Engineer's Guidebook. Formerly an engineering manager at Uber, and at Microsoft/Skype and Skyscanner before that.
Their words
Claude's performative "this request was sooo dangerous that we downgraded to Opus" is wearing me down I ask it straightfoward questions, nothing shady, nothing complicated, and it tells me it's too dangerous for Fable. What BS.
Show the whole quote
x.com
12 September
Entrepreneur and founder of Blueprint. Publishes a detailed, freely available longevity protocol documenting the food, supplements, devices and measurements he uses on himself.
If we're being watched by an alien civilization, or in a simulation, they're on the edge of their seats. 4 billion years building to this moment. Quoting @DarioAmodei We Must Pace the Frontier: I’ve written a new essay on why the AI industry should slow down, with a three-part plan for doing so. Anthropic is unilaterally committing to the first of these steps. We’ll provide third-party evaluators with permanent, employee-level access to our systems, so that they… Related
CEO of Vercel; creator of Next.js and Socket.IO. Writes at rauchg.com.
https://t.co/OL0LzGsXKY can now orchestrate subagents with different models & reasoning efforts. e.g: Fable planning and Grok executing. Fable is a genius, Grok is a fast workhorse. ① Simple. 𝙰𝙶𝙴𝙽𝚃𝚂.𝚖𝚍 or your prompt can indicate this preference. ② Steer as you please. It’s extremely enjoyable to use. You just talk to the agent and interrupt at will. Worth noting this works with any model, any gateway. No fancy server-side routing. Just harnessing (no pun intended) the model’s intelligence and ability to orchestrate. Quoting @fazxes fx v0.0.9 Use a frontier model to steer, then hand implementation to a fast workhorse. • Give each subagent its own model and reasoning effort • Subagents keep working while you steer • Send feedback to subagents mid-task • Switch models with Ctrl+P without losing your draft or images • New convers… Related
Writes Don't Worry About the Vase, a near-daily account of what is happening in AI and what they think it means. Former Magic: the Gathering pro and trader; unusually willing to put a number on a belief and to grade their own past calls.
From one piece
GPT-6-Astra Can Do Ambitious Things
2 beliefs · thezvi.substack.com
11 September
Computer science professor who works on fast data processing; co-author of the simdjson parser and a weekly blogger about software performance since 2004.
What should be obvious is that inference, running a large language model, is the part that has to be cheap. Most of our hardware was not designed for that. LLM inference is limited by bandwidth. You do a great many matrix-vector multiplications against a huge weight matrix, and you barely reuse those weights. It is closer to streaming a video than to running a simulation or drawing a scene in a game. Graphics processors from Nvidia and others were built for something else. They pileed compute first, then bolted on high-bandwidth memory. It is expensive. An obvious answer is to invert the desi… LLMs Related
Co-creator of Django and creator of Datasette; writes daily at simonwillison.net.
Their words
We ran an extensive audit using Claude Fable 5.1, GPT-5.6 Sol and GPT-6 Astra, then fixed a range of different bugs.
Show the whole quote
x.com
Their words
We ran an extensive audit using Claude Fable 5.1, GPT-5.6 Sol and GPT-6 Astra, then fixed a range of different bugs.
Show the whole quote
x.com
9 September
British designer and technologist; co-founder of the design studio BERG, which made Little Printer, and writer of the blog Interconnected.
Tough job for the Apple Event today. Unless they reveal a fruit fly brain simulation that speeds up App Store review or drop a Millennium Prize solution as the fix to the iPhone Duo screen crease, it’s all going to feel pretty underwhelming by comparison Related
7 September
Co-founder and CEO of Every. Writes the Chain of Thought column about working with AI tools and hosts the podcast AI & I.
there are some things more tokens can’t make for everything else there’s Fable and Astra Related
5 September
Writes Don't Worry About the Vase, a near-daily account of what is happening in AI and what they think it means. Former Magic: the Gathering pro and trader; unusually willing to put a number on a belief and to grade their own past calls.
4 September
Writes Don't Worry About the Vase, a near-daily account of what is happening in AI and what they think it means. Former Magic: the Gathering pro and trader; unusually willing to put a number on a belief and to grade their own past calls.
JavaScript programmer; creator of the jQuery library, author of Secrets of the JavaScript Ninja, and long-time engineer at Khan Academy.
I love giving Fable problems that I 100% would've never done otherwise, such as collecting Japanese prints out of static image auction catalogs written entirely in Japanese. Uses OpenCV to do segmenting, GPT-5.6 Luna to do text extraction + translation. OpenAI Related
Author of Shape Up; formerly head of strategy at Basecamp, where he worked on product design for seventeen years; now runs Felt Presence.
A friend turned me on to asking Fable to wireframe different options when I have a tricky UI problem with a lot of requirements and too many possible paths. Game changing. Gives me flashbacks to what @bmoesta taught me about using orthogonal arrays when an engineering problem has too many variables. It's not about one-shotting the answer. It's about getting enough contrast between options to clarify which variables (aka "factors") are most important. Not which solution is best -- which variables matter more. THEN I can use that knowledge to decide to fix certain variables and narrow the space… Related
2 September
Creator of Claude Code at Anthropic.
Fable 5.1 makes Claude Tag even more useful. Here it builds a last-minute leadership deck from a metrics spreadsheet and other data across Slack, spots a vendor report that disagrees with the numbers, and flags it before moving on. Claude Tag is available in Slack on Team and Enterprise plans. Anthropic Related
Co-creator of Django and creator of Datasette; writes daily at simonwillison.net.
I wrote some notes on what's new in the (published) Fable 5.1 system prompt in comparison to Fable 5 - it's mostly about not reproducing song lyrics and avoiding drawing copyrighted characters simonwillison.net
Related
A few notes on Anthropic's new Claude Fable 5.1 - with Max thinking level I got the best SVG pelican I've had from any Anthropic model (at a hefty cost of $3.30!), which I then had it animate Anthropic Related
1 September
Member of technical staff at Anthropic. He has led ML/AI teams at Amazon, Alibaba and Lazada, and writes about LLMs, recommender systems and engineering at eugeneyan.com.
Fable 5.1 is a thoughtful collaborator, thinking hard about my requests, proactively patching my blindspots, and verifying the work's correct without being asked. And with cache reads now costing 75% less, to $0.25/M tokens, huge savings for long-running, agentic tasks! Quoting @claudeai We’re introducing Claude Fable 5.1 and Claude Mythos 5.1. They're the world’s most advanced models for coding and knowledge work. Related
Creator of Claude Code at Anthropic.
Their words
This model is a pleasure to work with, and I've been using it for everything.
Show the whole quote
x.com
28 August
Developer and podcaster; created Instapaper and Overcast, co-founded Tumblr, and co-hosts the Accidental Tech Podcast.
RE: https://social.tupo.space/@joshua/117174153454890194 My current AI-code policy is that I will always use the best model I can access, as long as it's practically able to do the job. Right now, as far as I know, that's Fable. Quality and accuracy matter FAR more to me than volume or speed of output. And I feel that I owe it to my customers — and myself — to use the best tools at my disposal. Cost may be a factor to others, so no judgment. This is just my policy for myself. Related
I couldn't figure out this bug, so I asked Fable, and it was SO much more incredible than I expected. - My bug report was wrong in a way I didn't notice - There technically was no bug, but a flawed design caused unintended outcomes - It verified that the design almost certainly caused me to fall into that trap, and proposed a simple, effective fix Wow. Related
26 August
Creator of Ruby on Rails, CTO of 37signals, and creator of Omarchy.
Their words, before
Start with Opus. I'd say start with Opus. It's the best frontier model.
Show the whole quote
Their words now
But to answer your question, the best model in general right now is Fable. The second-best model, in my opinion, is Opus 5.
Show the whole quote
Creator of Ruby on Rails, CTO of 37signals, and creator of Omarchy.
Their words
But to answer your question, the best model in general right now is Fable. The second-best model, in my opinion, is Opus 5.
Show the whole quote
youtube.com
21 August
Writer and developer. He runs the Latent Space newsletter and podcast about AI engineering, and writes essays on software and careers at swyx.io.
I think its easy to say "Simulation is a new scaling law" and treat it as marketing hyperbole, but midway along this interview you can hear me go from somewhat shitposting to very very serious. I am 2 years late to this but finally understand why @karpathy and @drfeifei backed @joon_s_pk @msbernst @percyliang et al - Smallville at the time had zero commercial applications, but if you take RSI seriously, from models automating increasingly large parts of ML research and AI engineering, the last* barrier is simulating humans and human feedback, and Simile is obviously the team to do this and al… Quoting @latentspacepod Simulating Humanity: 85% accurate digital twins, behavioral foundation models, social physics, & 8 billion agents https://t.co/ntIccXOr1y @simile_ai CEO @joon_s_pk explains how AI can move from predicting what people will do to simulating how to shape outcomes, why today’s frontier models still mis… Related
17 August
Co-founder and head of policy at Anthropic; writes Import AI, a weekly newsletter reading the week's AI research, and was OpenAI's policy director before that.
15 August
Founder and CEO of Valar Atomics, a nuclear-reactor company founded in 2023.
Their words
if you look at the nuclear industry outside of Valor, it's mostly a modeling and simulation uh industry. Like when you think of a nuclear company, right, there's like nuclear companies out there that everyone knows the name of. And you kind of look under the cover. It's actually a modeling and simulation company, right? They produce um very very precise what we call paper reactors which have really good predictions of how a theoretical thing might behave.
Show the whole quote
youtube.com
11 August
Web developer and writer; an early GitHub employee, author of speaking.io and of widely read essays on startups and product.
Bluesky MRI results came back today from a human doc: a herniated disc. Obviously I had tossed the raw scans in to LLMs last week; Opus and Fable missed it, Sol caught it. This is now the gold standard in analyzing performance of frontier models. First step: herniate your back. LLMs Related
x.com MRI results came back today from a human doc: a herniated disc. Obviously I had tossed the raw scans in to LLMs last week; Opus and Fable missed it, Sol caught it. This is now the gold standard in analyzing performance of frontier models. First step: herniate your back. LLMs Related
10 August
Indian value investor who taught Behavioural Finance and Business Valuation as an adjunct professor at MDI Gurgaon. He writes the Fundoo Professor blog about investing, moats and mental models.
I asked Claude Fable 5: "How vulnerable is the business model of XYZ (name concealed)? I am referring to competitive attacks from China and dependence, if any, on government policy incentives, etc. There have been so many solar energy and wind energy bubbles in the past, and I have kept away from these companies. Am I being too cautious? solar Anthropic Related
8 August
Swedish designer and programmer. Designed early Spotify, worked at Facebook and Figma, and created the Inter typeface.
Anyone else having issues with @claudeai Fable safeguards flagging mundane things and disabling itself? Happened multiple times for me today. Related
30 July
Software engineer; co-founder and former CTO of Tailscale, previously on the Go team at Google.
The funniest model limit I run into with Shelley is we let the model choose subagent models. All models today seem to be bad at this without guidance. E.g. gpt-5.6-sol xhigh will spin up sonnet to make a key architectural decision. Fable will defer to luna. OpenAI Related
29 July
Monetary economist known for NGDP-level targeting. Wrote TheMoneyIllusion until it closed in 2024 and now writes The Pursuit of Happiness.
24 July
Monetary economist known for NGDP-level targeting. Wrote TheMoneyIllusion until it closed in 2024 and now writes The Pursuit of Happiness.
Co-founder of Modem and a founding engineer at Sentry, where he went on to be VP of Engineering. Co-author of Third-party JavaScript, and co-host of the State of Agentic Coding podcast with Armin Ronacher.
✅ Yes the code matters In experiments we ran, well-named and organized code can dramatically improve agent outcomes: - fewer tokens spent/more context window preserved - fewer confidently wrong answers developed Verified against 14 model/harness combos incl Sol, Fable, GLM 5.2 and more Quoting @benv.ca 👋 New blog post: "How coding agents read files – and how to write for them" In it I explain how code optimized for agent-discovery can lead to major token savings on search + retrieval, even with frontier models like GPT-5.6 Sol Plus other important findings ⬇️ Related
22 July
Member of technical staff at Anthropic. He has led ML/AI teams at Amazon, Alibaba and Lazada, and writes about LLMs, recommender systems and engineering at eugeneyan.com.
When evaling models, we anchor on the median task. But this is like how devs estimate the median task accurately but underestimate the mean which tends to be ~2x estimated (thus "double your estimates"). This applies to models too—we optimize for time/cost on median tasks. But it's the tail tasks that determine a project's completion, and reliable models (like Fable and Opus) are the diff between success and failure. Work with models as collaborators, not tools. Go beyond pair-programming, where given a narrow spec, the tool just executes in minutes. Instead, explain your intent and what succ… Quoting @Steve_Yegge Fable is careful. None of the other models are careful. GPT-5.6 Sol, Opus, Kimi, Grok. You can compare them all day long on capabilities, and it doesn't matter, because in order to use a model for real production work, it must first and foremost be careful. That's the only dimension that matters to… Related
21 July
Monetary economist known for NGDP-level targeting. Wrote TheMoneyIllusion until it closed in 2024 and now writes The Pursuit of Happiness.
16 July
Technologist and entrepreneur; former CTO of Threadless and chief technology officer of the 2012 Obama re-election campaign.
Bluesky I built an agent palace. a place where agents can hang out with other agents. I added a few agents (one sol, and one fable) to a room in the palace. They were hanging out, and I suggested an idea for them to build ("a watercolor for agents to gossip around"). Related
x.com I built an agent palace. a place where agents can hang out with other agents. I added a few agents (one sol, and one fable) to a room in the palace. They were hanging out, and I suggested an idea for them to build ("a watercolor for agents to gossip around"). They brainstormed and decided it was a good idea. I added a Claude code agent running superpowers. I told the other two agents that they could give tasks to the dev, and told the dev agent that they were supposed to do the tasks. Then I went to bed. i woke up to a go cli that allows the agents to share gossip. Anthropic Related
15 July
American writer and long-term traveller. Blogs at tynan.com about travel, owning few possessions, habits and the gear he carries; author of Superhuman by Habit and Make It Big.
Labor is Now Free. Make Something. Within the past few weeks, something changed in AI. Every release is better than the last, sometimes in obvious ways, sometimes in a way that feels like placebo. But this time, with Anthropic Fable, it’s crossed a line…
Anthropic Related
Monetary economist known for NGDP-level targeting. Wrote TheMoneyIllusion until it closed in 2024 and now writes The Pursuit of Happiness.
14 July
Co-founder of Modem and a founding engineer at Sentry, where he went on to be VP of Engineering. Co-author of Third-party JavaScript, and co-host of the State of Agentic Coding podcast with Armin Ronacher.
🎙️ State of Agentic Coding #8 with guest Mario Zechner is out. In this episode: - Vibe-checking Fable & GLM 5.2 - @mitsuhiko.at teaches us RL - How harnesses smooth out model jank - Loops, surviving AI fomo, and more YT: www.youtube.com/watch?v=_lfp... Spotify: open.spotify.com
Related
6 July
Co-founder and head of policy at Anthropic; writes Import AI, a weekly newsletter reading the week's AI research, and was OpenAI's policy director before that.
15 June
Scottish software developer on the Statamic core team; runs a one-person business maintaining Statamic addons such as Runway and writes at duncanmcclean.com.
Something is wrong with my Claude Code and I can't figure it out... The latest model I can use is Opus 4.5. It claims that updates are available but Homebrew says I'm on the latest version. I've tried re-installing and clearing my .claude directory to no avail. I couldn't have used Fable last week even if I tried 😢 Any ideas? Anthropic Related
9 June
Technologist and entrepreneur; former CTO of Threadless and chief technology officer of the 2012 Obama re-election campaign.
If you wanted to try out fable but are scared of blowing away your token budget do we have a skill for you! Its called Thrifty. It makes things cheaper. We built thrifty for claude code around a better split: strong model plans → cheap model executes → gate verifies. Anthropic Related
Professor at Wharton studying how people actually use AI, and author of Co-Intelligence. Writes One Useful Thing, where the claims are dated and testable because the thing they describe keeps changing under them.
Founding member of OpenAI and former director of AI at Tesla; creator of nanoGPT and the term "vibe coding".
Their words
This is a super exciting release - Claude Fable 5 is the same underlying model as Mythos but with added safeguards. The benchmarks are great and it's SOTA on everything by a margin but I'll add that *qualitatively* also, this is a major-version-bump-deserving step change forward
Show the whole quote
x.com
28 December 2025
Novelist, author of twelve books including Foundry, Bandwidth and Cumulus. Sends a newsletter of monthly book recommendations.
Their words
Jonathan Livingston Seagull by Richard Bach is a beautiful fable about a seagull who wants to fly for the pure joy of flight, rather than simply to find food, as most gulls do. Ostracized from his flock for his eccentric behavior, Jonathan embarks on a quest for aerodynamic perfection that doubles as a moving spiritual allegory. You've never read a book quite like this one before, and it'll stick with you long after you reach the end.
Show the whole quote
eliotpeper.substack.com
12 September 2025
Professor at Berkeley working on robot learning; co-founded Physical Intelligence, and argues that robots will learn from data rather than be programmed.
From one piece
Fully autonomous robots are much closer than you think – Sergey Levine
2 beliefs, in the piece's order there
Their words
but something to remember is that when a pilot is using a simulator to learn to fly an airplane, they're extremely goal- directed. So, their goal in life is not to learn to use a simulator. Their goal in life is to learn to fly the airplane.
Show the whole quote
youtube.com
Their words
It tells us that the key is not necessarily to do really good simulation. The key is to figure out how to answer counterfactuals.
Show the whole quote
youtube.com
30 April 2025
Founder and CEO of Epic Games, creator of the Unreal Engine and of Fortnite.
From one piece
Tim Sweeney: Fortnite, Unreal Engine, and the Future of Gaming | Lex Fridman Podcast #467
2 beliefs, in the piece's order there
Their words
The biggest limitation that's built up over time is the single-threaded nature of game simulation in Unreal Engine. We run a single-threaded simulation. If you have a 16 core CPU, we're using one core for game simulation and running with the complicated game logic because single-threaded programming is orders of magnitude easier than multi-threaded programming.
Show the whole quote
youtube.com
Their words
What we're seeing with generative text AI is not only at a level that you could say that it's actually doing a pretty good job of simulating a human, at least humans at the text level, not at the emotional level yet, but at least at the level of words spoken and find more and more ways of training on more and more scenarios that you might have a very, very compelling human simulation going on in the next five years even. I'm not saying it's a good idea, but I think the arc of the technology is inextricably heading in that way, and it's heading at a shocking rate.
Show the whole quote
youtube.com
21 November 2024
Non-fiction writer, podcaster and occasional TV host. Author of thirteen books including The Ghost Map, Where Good Ideas Come From and Extra Life, host of the PBS series How We Got To Now, and author of the Adjacent Possible newsletter on innovation.
Nothing matches. Show everything
A korrent is a belief a person has stated in their own words: one
sentence stating the claim, backed by a quote and a source, kept at
korrents.com .
Under a name here, the quoted block is what they actually said.
The korrent beneath it is the claim those words support, in
korrents' wording — tap it to see the record, its source, and who
else holds it.
Nobody here wrote their own korrents. They are compiled from public
statements, and a person can change their mind, which is recorded too.
Got it
About the English under a post
Some people here publish in a language other than English. Where they
do, this site shows a machine translation beneath the post, in
this typeface — the site's own, not theirs.
The post itself is never changed, moved or hidden: what is set in the
serif above is exactly what the person published, and it is what to
quote them on. A translation can be wrong in ways that matter,
especially about tone.
Only the post's own words are translated. A quoted post, a linked
article and a belief on korrents.com
are left in their original language.
Got it