Reading up on Fable
43 deep · digging since jun 10
- Fable & The End of the Free Lunch
The author argues that after Fable's high-cost release, developers must allocate work between expensive models and cheaper alternatives like GLM, ending the era of free performance gains.
- Testing Fable vs Sol in terms of taste (they are both bad)
When given identical briefs, skills, and Magic Hour credit budgets to create four films each, Fable and Sol both yielded videos judged as low‑quality, indicating comparable shortcomings in taste.
- AI is removing the middle class of software engineering
AI enables rapid code generation, allowing engineers with weak judgment to create unmaintainable systems faster, exposing and amplifying poor engineering practices until projects collapse under their own complexity.
- How Cursor Router chooses the right model for the task
Cursor Router uses real developer traffic data to automatically select the optimal AI model for each task, balancing cost and performance through Compass complexity prediction and a learned taxonomy.
- The Shape of Things to Come, Part 1: The Continuous Thunderdome — Steve Yegge
Yegge demonstrates that a Beads‑driven orchestrator with rotating Claude Max accounts lets agents run nonstop loops, eliminating CI/CD and human code review for his Wyvern MMO.
- Prompt Caching In Agents
Prompt caching is crucial for coding agents’ cost and latency, but fragile; Pi maintains stable inputs and exposes cache metrics to help users manage performance.
- Building Accessibility Into a Canvas-Based Product
Figma created a Mirror DOM and internal accessibility tree to give screen readers full navigation and announcement support in its canvas‑based editor.
- A Fireside Chat with Cat and Thariq from the Claude Code team
Claude Tag now handles 65% of the Claude Code team's product engineering PRs, and the team reduced Claude Code's system prompt by 80% thanks to newer models.
- China’s Latest A.I. Breakthrough Threatens America’s Lead
China's Moonshot AI released a free AI model that narrows the performance gap with leading U.S. models, matching or exceeding them in certain benchmark tests.
- The Pulse: What can we learn from Bun’s rapid Rust rewrite with AI? - The Pragmatic Engineer
Bun’s Zig-to-Rust rewrite was completed in 11 days using 64 AI agents, costing $165K, showing AI can accelerate large migrations when a solid test suite and expert oversight exist.
- Fable's judgement
The author learned to let Claude Code's Fable model use its own judgement to delegate coding tasks to lower-power models, improving efficiency and token usage.
- You're Spending Too Much on AI. You're Also Using Too Little.
Companies overspend on AI by using costly frontier models for routine work, needing better defaults, outcome-based measurement, and cultural efficiency incentives to unlock far greater value.
- Anthropic’s Safety Superpower – Stratechery by Ben Thompson
Anthropic's genuine belief in safety licenses it to prioritize business interests and challenge the U.S. government.
Takes
folks that orchestrate: what's your workflow? seen lots of folks say the "plan with fable, implement with XYZ". how? what's the UI/UX/flow/tooling for that?
@Shpigford
Fable one-shotted a Rust rewrite of the TerminalTextEffects Python library in 11M tokens. Startup time went from 87ms to 2ms and rendering speed is up by 9.6x. Now zero dependencies and a 3mb single exec 🤯 https://claude.ai/code/artifact/287825bc-7aad-4541-a7e7-fa4ba8d03612
@dhh
@lennysan @lukeharries Would it be useful to have an http://elevenmusic.io connector in Claude? Would give fable full creative freedom over our incredible music v2 model
@louisjoejordan
I reviewed a Redis me optimization and was about to submit the PR. Then I said myself: "wait, we are in 2026" and wrote a script that calls Sol and Fable at each turn, challenging to improve the work of the previous one... Soon to be continued with the results.
@antirez
Fable is really good at launch videos It essentially one-shotted this video. I told it to read my launch post and create a launch video. That's it. It ran for 46 minutes (without asking me any questions), found all the product logos, and spit this out. I then asked it to add music, so it logged into my @ElevenLabs account within my Chrome, generated the music, and mixed it in. Wild.
@lennysan
I thought it was another game one shotted by Fable, my brain is fried 💀
@linuz90
Setting up Fable to use Codex 5.6 Sol as a subagent was the best idea ever—Fable is super great at supervising but pretty slow at executing on its own and Codex is really fast but needs a nanny. Perfect combo.
@SnazzyLabs
many people asked me how i keep shipping when on my phone i have my own ios app and here’s a quick clip of how i use it: - ssh to my mac mini - never open the mobile keyboard - it sucks. instead i designed this touch “dial” - voice input for prompts using on-device transcription model - i can also send images directly from phone do you like this kind of interactions? i actually had to design the “dial” myself. both fable and sol failed to come up with this solution - they kept building different button rows. fable called me clever when i showed it this idea :)
@kunchenguid
Introducing Impeccable 4 *world builder* However many ways you ask, "be creative!!!" does nothing to an LLM. v4 cracks it, and greenfield work is where it shows. • a creative engine for greenfield and redesign: directions seeded and fused from hundreds of human-approved visual worlds • hyper-optimized for frontier models (GPT 5.6, Fable and class), on a core 58% smaller • far simpler to use: no command to learn, it works out the job itself (blank slate, redesign, added section, scoped refinement) • mobile app design, the #1 request, now in alpha: Apple HIG or Material 3 on top, audit and adapt running as VoiceOver and TalkBack passes • Grok Build and Mistral Vibe join the supported harnesses • plenty more
@pbakaus
I think loops were a short-lived patch for models that couldn't reliably keep working on long problems until they hit a defined goal Fable and GPT-5.6 (and probably Kimi K3 as well) can just do that out of the box, unassisted
@simonw
Fable just found a 15-30% memory efficiency improvement in Turbopack / Next.js, nearly autonomously. @tobi asked me today: what have been your “holy s***” moments with AI? My answer was: it’s every single week. And it’s accelerating. In fact, “WTFs/day” might just be my favorite metric for AI progress. It’s one thing to read benchmarks or stories online. It’s another to watch these machines pull engineering feats every day. 3 days ago? Sol helped us find novel vulnerabilities in some of the most audited code in the world. Today? Fable helps us ship this large optimization of a very complex Rust codebase. I just saw some results of work we’ve done to shrink binaries by 10-20x. List goes on.
@rauchg
my new favorite of way of using fable: step 1. ask it to write a plan step 2: "please get second opinions from codex CLI using gpt-5.6-sol @ max effort and kimi CLI using kimi 3. Revise your plan with any sound findings. repeat until convergence or up to 5 rounds."
@blader
How to code with Kimi K3 (better than Fable and no restrictions) today: - Ask Codex or Claude Code to install OpenCode (yes it will 😂!) - Go to
@levelsio
this has 0 manual edit and was done by Fable with Revid MCP crazy simple to use the MCP 👇 https://www.revid.ai/mcp
@tibo_maker
I had Fable build another thing I always wanted, a full procedural fantasy kingdom generator with economics, trade routes, population growth, wars, lineages, and occasional dragons. First, I worked with it on a plan, then it made it. You can play it here: https://annals-kingdom.netlify.app/
@emollick
I had early access to 5.6/Sol for ~month. Sol is my default. It is faster, plans/judges just as good as Fable, and I think produces better overall work. I’ll reach for Fable still for highly targeted debug or performance work with clear reward functions. A cheeky way I describe Sol vs Fable to my friends is that Sol is a charismatic, efficient, talented coworker you’re jealous of. Fable is a genius recluse that is brilliant at its fixations but doesn’t go out, doesn’t date, and you don’t want to hang out with them much lol. Fable is undefeated at highly targeted debug/security/performance goals. It’s a sight to behold and I was never able to get Sol to push as hard in this category. I’ll keep using it for this. Sol is better or comparable at everything else, in my experience. Give it a shot, it’s hard to describe but it’s just more enjoyable to work with. (Disclaimer I have no financial ties to either lab, wasn’t paid for any of this.)
@mitchellh
If you run this workflow, ask Fable to make codex the workhorse. https://github.com/steipete/agent-scripts/blob/main/skills/codex-first/SKILL.md
@steipete
What The New 100x Agentic Engineer Looks Like In The Era Of Fable & GPT 5.6
@systematicls
I built an engine for Fable to create its own self-improving NPC town with @threejs and it's actually doing it lol. Literally shipping its own PRs to advance the story and lore. Crazy.
@gill_works
Fable is pure magic. I wanted a beautiful app to explore ocean wildlife. Fable built this in an hour. It generated videos with Seedance and carefully synchronized them to make these absolutely insane transitions. I've never seen anything like this in an app. Unreal.
@anshuc
Fable 5 is so good at web design that I genuinely don't see how web design careers make it past the end of this year. An AI that can one shot designs this good means that the web design industry as a whole is in serious trouble. If you're in web design, it's time to pivot.
@markgadala
I’ve found the most important part of working with Fable is discovering my own unknowns so I can prompt it better, heres how I do that.
@trq212
The Window Has Closed
@AndrewCurran_
The Physics of a Fable
@Rafa_Schwinger
You should basically never use Fable for coding, but instead use it as a planner/orchestrator. Most of today's advanced models can implement a spec perfectly, and once done you can send the work to Fable to review. This has been my most powerful flow so far.
@skirano
oh ok i get it. imagine you have a staff engineer working on a basic CRUD saas. and they complain year after year you're not working on enough tech debt and nothing is ever prioritized right. and then they propose the most opaque, overwrought example of backend performance issues, and try to convince your ceo that you should stop all product development and put 100% of your engineers on fixing your flaming dumpster fire of a monorepo. and every year you say no, because their proposals are intractable, completely untied to business metrics, and "no customer will care." now pretend you can put that person in a back room and ignore them for a few days, and they come back and secretly ship everything that was wrong in your repo. your app is now blazing fast and you are at bug zero. that is how you should use fable. (just don't put him in a meeting, and don't let anyone read his docs)
@clairevo
Lots of people asked how I used Fable to edit its own launch video so I made a video about that! TLDR it wrote a lot of code & tool calls to use transcription services, ffmpeg, do colorgrading, use the figma mcp, make remotion UI and render it. I didn't touch a video editor.
@trq212
Fable is a good model. As with all new models, it is simultaneously excellent and entirely unremarkable (relative to other models). It is slow and expensive, and the "loops are all you need" discourse they are pushing is obvious in the context of someone using Fable-class models What I've found so far is that for broad scope design (code architecture) tasks, Fable is unremarkable. Or, not better enough to justify its cost and speed. But in highly targeted goal-oriented loops, it is another beast entirely. It is very slow but produces very good results. I let it churn on optimizing a SwiftUI-layout resolver in Go I wrote and it was able to bring it down to an order of magnitude I could not reach myself (micro => nanosecond scale). But it took 2 hours and $40 to do it and I had to claw back some changes it overfit to Apple Silicon. Still, very worth it. In comparison, for "implement this feature/change" iterative work, I ran head-to-head Fable vs GPT5.5 vs. GLM-5.1. They all produced equally acceptable final results, but GPT5/GLM did it in a couple minutes and Fable was churning away for 40 minutes. And GLM cost me less than a dollar, GPT5.5 ~$1.50, and Fable cost $9. You can see that in this context, interactively working with an agent is nonsense. Its too slow. You need to write loops to keep the agent working and you probably want to highly parallelize the work being done. As with all things, I think a balance makes sense... My sense is that I'd reserve Fable for targeted, surgical analysis and work. Not for daily driving everyday tasks. I'm going to keep spending a shitload of money (relatively) and maining Fable for the rest of the week to continue to judge, will report if anything changes. I'll continue to head-to-head as well.
@mitchellh
How are you guys feeling about Fable so far?
@theo
I gave Fable this tweet and let it crank in ultracode. It created a fully functioning multiplayer markdown editor with obsidian style editing, version history, sharing with email invites, cli sync with a skill, image support, deployed it to cloudflare and bought a domain.
@sawyerhood