Built mission control for the new class of AI agents that work in hours, not minutes using the new Claude Fable 5 model. The chart redraws the thesis on a loop: two models track together on short tasks, then the lead compounds as the horizon grows. You walk in at hour four of the agent's shift.
we just wrapped our Spring quarter at @diabrowser. before i jump to the next big thing (!), a short behind-the-scenes on one of my favorite projects to date: artifacts!
the design challenge: how do you make AI-generated docs that don’t *feel* AI-generated? (🧵 1/10)
We're trying a new experiment at @cursor_ai - interviewing devs we admire.
I chatted with @oneill_c & @part_harry_ from @baseten about how they use coding agents. We discussed their current dev workflows & some predictions for the future.
Check it out below!
@MysterE___@andrewmccalip Correct I don't want to lose focus on what im doing as I'm working personally, also when were users ever actually paid to view ads while paying for a product? I'm sure there's a reason Anthropic wouldn't introduce this into their product anytime soon.
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.
cool internet things pt. 6
https://t.co/wTGYG7tYm3 - math visualized
https://t.co/09hFmr9csj - visual instruments
https://t.co/H7iFmVtUFu - every music genre ever
https://t.co/uTCkmA9wVf - a camera that prints poems
https://t.co/m4LrYSv4ib - digital stamp collection
https://t.co/447WHCUPFY - a living digital sketchbook
some of the cool people behind these:
@michelletliu, @marijanapav, @rpavlini, @S_Conradi, @EveryNoise, @S_Conradi, @itsjessyin, @kelin_online
@MysterE___@andrewmccalip No I am saying I am already paying for Claude to use claude and its features for my ai workflows and do not want that experience inconvenienced by ads.
I've been a backend Engineer for 12+ years. Today, I'm a Principal Engineer at Atlassian.
I've designed systems that handle millions of requests. Sat on both sides of system design interviews.
Reviewed more architecture docs than I can count.
Starting today, I'm breaking down the fundamentals of scaling for the next 25 days.
If you're learning system design bookmark this thread, you're going to get a lot of learning from this.
Built mission control for the new class of AI agents that work in hours, not minutes using the new Claude Fable 5 model. The chart redraws the thesis on a loop: two models track together on short tasks, then the lead compounds as the horizon grows. You walk in at hour four of the agent's shift.
looking for a designer who's good with claude code. you bring the taste, claude writes the code, you direct it.
europe timezone overlap, fluent english, bit of github comfort.
paid. dm me with work you're proud of + how you use claude.
Claude Fable 5 took my 4 months of fine-tuning work and made an end-to-end 7-stage pipeline that i can sell.
It took 3 hours of /goal.
> Built TUI,
> html dashboard,
> html dataset viewer,
> crafted 39 special skills,
> wrote 8700 lines of code,
> ran 235 tests.
And the pipeline in 98% ready in one-shot. Shipping this soon.
Mythos / Fable is unbelievable.
Was on a customer call today and had Claude transcribing in the background.
As they were telling me about the features they wish their current software had, Claude was building the features in real time.
By the end of the call I was able to show a fully working product, with the exact workflow they mentioned 15 minutes earlier.
Autonomous looped building triggered from a customer call. 🤯
One of my personal favorite features announced at WWDC will I suspect be a sleeper hit: container machines, allowing your Mac to run a lightweight, persistent Linux environment with your home directory and repos automatically mounted: https://t.co/dOBdfOOVxC
Asked Fable to build a navigable version of Yosemite to scale
> pulled satellite imagery + real NASA elevation data
> classified individual forest pixels and created ~266k procedural trees
> custom water shaders for all 6 famous waterfalls + accurate placement on cliff brinks
> five times of day: dawn to night
> tested itself: flew the camera around headlessly, screenshotted its own work, and fixed tree colors + waterfall placement from what it saw
> added snow etc. unprompted
Pretty fucking impressive