Thibault Sottiaux
Cyber team wants your feedback on Daybreak. Models, codex plugins, blue/red access, documentation, red teaming & defense factory... What can we do better or improve?
Cyber team wants your feedback on Daybreak. Models, codex plugins, blue/red access, documentation, red teaming & defense factory... What can we do better or improve?
Two very useful prompts to try with Fable 5.2:
"/doctor prompt-audit": Audits your Claude Code setup (Claude md, skills, commands) and proposes fixes.
"/claude-api prompt-audit [skill name]": Audits one skill in depth.
I wish Claude Code auto-suggested running these every time Anthropic releases a new model.
📌 Watch my full tutorial on how I use Fable and Opus here: https://t.co/slyEbWvvqA
And please consider starring the repo to help more people discover it: https://t.co/gcEOz8a8sw
An awesome day for humanity
✦ ·
✧
· ✦ ·
✧ ✧
· ✦
✧ · ✧ https://t.co/PFq6pBdxcS
Got to experience the magic of @uisdk.
Two prompts of fx + Gemini Argon. Pure Web Components. No framework.
The agent reused 14 UI SDK behaviors out of the box 🤯: window resizing, drag, menubar hover-switching, typeahead, roving toolbar focus, 10-band EQ sliders, scoped hotkeys, ARIA, and WebMCP agent control.
https://t.co/1Ol3xqKWJz (source linked)
Music by @suno.
Subagents on https://t.co/3Z4NESzNKd work so well… extremely delightful. Amazing how much goodness fits in 6.33mb 😁
All my projects are built by planning with the smartest model + delegating to fast model subagents. It's a 1-line instruction in ~/.𝚏𝚡/𝙰𝙶𝙴𝙽𝚃𝚂.𝚖𝚍. https://t.co/27S2By5smT
Autonomous Businesses are here. https://t.co/4pISz57GP9
Technology is inherently recursively self-improving and the degree of autonomy has been going up overtime. AI is an accelerant but it didn’t not start this cycle.
Douglas Engelbart understood this. https://t.co/J3Zp1YNFXC
We’ve entered Murphy’s world. Anything that can go wrong will go wrong. With billions of things happening at once, recursively interdependent and accelerating rapidly, what’s once considered a rare failure is now a daily thing.
AI models are inevitably going to keep getting better and better at all coding, tool and computer use, math, and other coding-related tasks. As a result, agents that can use software to do their work, or generate code from scratch, will improve at a faster rate than all other domains of knowledge work.
On one hand that could mean that only a small subset of work can get automated. But probably what happens is that more and more work just becomes coding-shaped to adapt to what agents are good at.
You can see it in the most recent examples of model releases in the past couple of months, where agents can generate code that becomes animated videos, games, 3D models for products, and so on. We also know that tool use gives agents the ability to work with much of the same software that people already work with. This helps in cyber, life sciences, finance, and a number of other domains.
Our mental model traditionally has been that the models have to be able to know everything about anything to generate value, but in reality they *really* have to know how to use or generate software effectively combined with deep domain expertise to make the right judgment calls inside of workflows.
When you have that powerful combination, almost everything else gets unlocked. This is why the acceleration of agents in knowledge work is only going to increase from here.
Aside Browser is a huge unlock for every AI agent https://t.co/lo8Tgqnu9J
Do all this and use it with gbrain :-) https://t.co/WxlVS6Elf9
It turns out paper chart and copper wire and an antiquated system that is brittle and doesn’t have enough failsafe let alone any modern software is not serving the people of America properly.
Modernize the FAA. https://t.co/J4wbogmVSy
live look of how Fable wrote an email for me this morning https://t.co/DfgwzjXHeG
experiment writeup + code here: https://t.co/T92y6fRzit
if you want all of the raw alpha from @every you should have your agent read our frontier feed
we publish all of our frontier team's experiments with AI including raw code and short writeups
no faster way to get inspired 👇
https://t.co/S9TTJQsfnB https://t.co/yN5rjLUWxr
holy shit u guys like a lot of poteto https://t.co/vZn94FofDx https://t.co/39aoCIMcSK
obviously correct, we are so suboptimal in AI UX rn it is crazy esp given existence of models too cheap to meter https://t.co/6S0eWejPXK
there WILL be audience participation https://t.co/GqGaekFHtl
Available to all Gemini app users in the USA to start
https://t.co/LMhEmp58DA
New in Gemini: Connect Google Wallet for personal finance insights
This is powerful for things like:
+ making instant charts to visualize your spend
+ finding sneaky subscription price hikes
+ making a holiday budget based on what you actually spent last year https://t.co/wzrBpwYpxm