Partial day — headline is the last complete day (2026-10-13).
twitter
tracked since 2026-10-11T15:40:47.994215+00:00
conclusion
Measured mentions per day
day (UTC)
mentions
2026-10-04
4
2026-10-05
8
2026-10-06
6
2026-10-07
8
2026-10-08
7
2026-10-09
4
2026-10-10
3
2026-10-11
4
2026-10-12
10
2026-10-13
3
2026-10-14
0
derived from
explore
word-boundary match over title + text, query='timeline' · window
2026-10-04 → 2026-10-15
· 57 matching posts
evidenceShowing 20 newest of 57
•
twitterIbelick20hpositive
new skill: component-canvas.
it puts all the components from a repo on a canvas, with all their variants and states.
a nice way to explore the UI of a codebase. https://t.co/HumaAEWAcinew skill: component-canvas.
it puts all the components from a repo on a canvas, with all their variants and states.
a nice way to explore the UI of a codebase. https://t.co/HumaAEWAci
THIS IS F*CKING BRILLIANT. Anthropic’s docs describe one of the smartest ways to run Opus
three models work on one task and each does only the part it’s cheapest at. start Claude Code like this:
claude -> model sonnet -> advisor opus
you stop paying Opus prices for work that doesn’t need Opus
> Sonnet runs the sess…THIS IS F*CKING BRILLIANT. Anthropic’s docs describe one of the smartest ways to run Opus
three models work on one task and each does only the part it’s cheapest at. start Claude Code like this:
claude -> model sonnet -> advisor opus
you stop paying Opus prices for work that doesn’t need Opus
> Sonnet runs the session and edits the code
> Haiku 5.5 searches the repo and docs, at up to 40x less per token than Opus 5.5
> Opus waits as the advisor and reads the whole session, tool calls included
Claude usually calls Opus at three points:
> before it locks a plan
> when the same error comes back
> right before it says it’s done
Sonnet drives. Haiku scouts. Opus signs off
and if you go one step lower, most of an agent’s day is tiny choices like picking a file or a tool, or deciding whether to retry. Jev takes those first, so Sonnet and Opus only see the moments that are really open
the whole setup
Sonnet runs the main session
Explore on Haiku 5.5 searches and pulls docs, read-only
Opus on call as the advisor
give Claude Code this setup and the prompt below ↓
“Set up my Claude Code exactly like this:
Main model Sonnet, advisor Opus, saved as advisorModel in my settings.
One read-only subagent named exactly Explore, on claude-haiku-5-5, to replace the built-in one.
One line in CLAUDE.md: ask the advisor before locking a plan, after the same error twice, and before calling a task done, not more often.
Check what could turn the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) and only report it.
Show every change as a diff first. Don’t edit anything until I say go.”
https://t.co/xpEE0hFQ6d
before you turn it on:
every advisor call re-reads the whole transcript with no cache. on a 200k session that’s about $0.80 in input, against $0.04 for a normal request. keep it to a few calls
the built-in Explore agent runs on your main model unless a subagent is named exactly Explore. any other name does nothing
turning the advisor on or off keeps y
stop making generic ai videos
use good harnesses that help you explore ideas like an artist
harness in comments https://t.co/XXtlnZZnPvstop making generic ai videos
use good harnesses that help you explore ideas like an artist
harness in comments https://t.co/XXtlnZZnPv
Coaches Corner powered by @awscloud goes Inside the Game with San Antonio Spurs head coach Mitch Johnson and ESPN analyst Tim Legler as they explore how Victor Wembanyama's gravitational pull creates gaps and scoring opportunities for his teammates. https://t.co/dFU400M5aCCoaches Corner powered by @awscloud goes Inside the Game with San Antonio Spurs head coach Mitch Johnson and ESPN analyst Tim Legler as they explore how Victor Wembanyama's gravitational pull creates gaps and scoring opportunities for his teammates. https://t.co/dFU400M5aC
Exciting news: Ask @YouTube on search is now rolling out on mobile in the U.S. 📲
Tap “Ask” in the search bar and use conversational questions to get you to the right video faster, for example:
🍂 Which national parks are best for fall colors?
🚗 What’s the best route for a 3 day road trip from SF to LA?
✂️ How to cut b…Exciting news: Ask @YouTube on search is now rolling out on mobile in the U.S. 📲
Tap “Ask” in the search bar and use conversational questions to get you to the right video faster, for example:
🍂 Which national parks are best for fall colors?
🚗 What’s the best route for a 3 day road trip from SF to LA?
✂️ How to cut bangs at home? (If you’re brave enough!)
Huge kudos to our YouTube teams for constantly innovating and reimagining how viewers explore. Give it a try next time you search.
more markets to explore, more charts to stare at.
my sleep schedule was already finished anyway 😭 https://t.co/3uyo1YPjjhmore markets to explore, more charts to stare at.
my sleep schedule was already finished anyway 😭 https://t.co/3uyo1YPjjh
We've spent a lot of time making AI agents better at reasoning and talking. Giving them a real-time visual presence is another interesting direction.
An LLM handling dialogue while a video model responds to scene and emotion signals? There's a lot to explore here.We've spent a lot of time making AI agents better at reasoning and talking. Giving them a real-time visual presence is another interesting direction.
An LLM handling dialogue while a video model responds to scene and emotion signals? There's a lot to explore here.
Get detailed investment advice with #KwalaIntel
The A to Z of the stock market, now in your own language!
Explore Now
https://t.co/Ox7JkaMlMQ https://t.co/dqE9HYiDyOGet detailed investment advice with #KwalaIntel
The A to Z of the stock market, now in your own language!
Explore Now
https://t.co/Ox7JkaMlMQ https://t.co/dqE9HYiDyO
AI agents make decisions constantly. The hard part is proving what an agent did and that no one edited the record afterward. 😖
Autonomys is the decentralized foundation for AI, with permanent storage available today so those records stay verifiable.
Explore the network 👇
https://t.co/HGdZFcUq4J
Try permanent storage…AI agents make decisions constantly. The hard part is proving what an agent did and that no one edited the record afterward. 😖
Autonomys is the decentralized foundation for AI, with permanent storage available today so those records stay verifiable.
Explore the network 👇
https://t.co/HGdZFcUq4J
Try permanent storage today 👇
https://t.co/X9WvzkeKlJ
22 new projects are live for week 2 at dotstore.
Explore, vote and help them secure top 3 spots. https://t.co/77s4fmOtc722 new projects are live for week 2 at dotstore.
Explore, vote and help them secure top 3 spots. https://t.co/77s4fmOtc7
gStar
Been checking out SuperEngine on Startale, and this one looks pretty interesting
SuperStake. fun brings an interesting idea to the table play games, build your own, and earn from what you create.
- Explore games built with SuperEngine
- Create your own game
- Earn from your creations
- Top 15 creators get wee…gStar
Been checking out SuperEngine on Startale, and this one looks pretty interesting
SuperStake. fun brings an interesting idea to the table play games, build your own, and earn from what you create.
- Explore games built with SuperEngine
- Create your own game
- Earn from your creations
- Top 15 creators get weekly recognition
The Builders Challenge features a $2K prize pool, and creators can keep 40% of their game's weekly profit, according to the information shared.
You can actually build something of your own and share it with the community. I'm curious to see what people create with SuperEngine
If you've been thinking about building a game, this might be worth checking out.
⚡ Explore and build on Startale.
Introducing Code Video Model 🎬
Amazing work led by @raywzy1 and the team!
Agentic coding as the engine for controllable video generation.
Scene layout, motion, timing, camera trajectories, and physical dynamics, all in editable code.
A coding agent turns prompts into executable programs that render proxy videos. Ou…Introducing Code Video Model 🎬
Amazing work led by @raywzy1 and the team!
Agentic coding as the engine for controllable video generation.
Scene layout, motion, timing, camera trajectories, and physical dynamics, all in editable code.
A coding agent turns prompts into executable programs that render proxy videos. Our training-free early-step conditioning lets a pretrained video model follow the proxy’s structure while adopting a reference image’s appearance.
From physics-grounded motion and bullet time to 3D/4D reconstruction and robotics simulation, it all starts with code.
Watch the demo and explore more visual results 👇
Project page: https://t.co/3eyhkYhR2t
Paper: https://t.co/VzHC03u9JN
Code: https://t.co/nspc5JM1A4
Data: https://t.co/18WMfQldOK
Youtube: https://t.co/ohyGXbKRZE
Wondering what should I build while I still have unlimited AI tokens.
Maybe it’ll be something related to history. I’m really passionate about it.
Thinking of building an app that allows you to create an interactive-kind-of-game from a period you specify. You explore and interact with the world from that period throu…Wondering what should I build while I still have unlimited AI tokens.
Maybe it’ll be something related to history. I’m really passionate about it.
Thinking of building an app that allows you to create an interactive-kind-of-game from a period you specify. You explore and interact with the world from that period through a VR headset.
Silver Pines, the search-action survival horror, is out now on PS5
Explore and survive in this mysterious tale: https://t.co/Ca02PawZQ8 https://t.co/4OHrcFaZxSSilver Pines, the search-action survival horror, is out now on PS5
Explore and survive in this mysterious tale: https://t.co/Ca02PawZQ8 https://t.co/4OHrcFaZxS
OPEN-SOURCE GITHUB PROJECTS FOR BUILDING AI AGENT MEMORY
An AI agent that forgets everything between sessions has a serious limitation.
These 10 projects explore how to help agents remember, retrieve, and use information over time.
1. Mem0
↳ https://t.co/arkWqTDdw9
Add persistent memory to AI applications and rememb…OPEN-SOURCE GITHUB PROJECTS FOR BUILDING AI AGENT MEMORY
An AI agent that forgets everything between sessions has a serious limitation.
These 10 projects explore how to help agents remember, retrieve, and use information over time.
1. Mem0
↳ https://t.co/arkWqTDdw9
Add persistent memory to AI applications and remember useful user context.
2. Hindsight
↳ https://t.co/XotUrjxRz0…
Build memory systems around retaining, recalling, and reflecting on information.
3. memU
↳ https://t.co/EKm5VbYp2m…
Explore memory infrastructure designed for AI agents and ongoing interactions.
K
everyone is building products with ai.
but who’s actually getting users? 💀
so we built ghosty 👻
your new ai launch agent from @_foundrlist 🚀
→ improve your seo
→ analyze competitors
→ discover growth opportunities
→ plan your product launch
→ explore advertising options
less busywork. more shipping.
you build the…everyone is building products with ai.
but who’s actually getting users? 💀
so we built ghosty 👻
your new ai launch agent from @_foundrlist 🚀
→ improve your seo
→ analyze competitors
→ discover growth opportunities
→ plan your product launch
→ explore advertising options
less busywork. more shipping.
you build the product. ghosty helps you launch it.
Introducing Anatomy
Describe a machine in one line. Claude brings it to life.
- Interactive isometric wireframes you can rotate, inspect and explore
- WebGL shaders for fire, water, plasma and more
- Real 3D motion, with individual parts that rotate and move
Install it as an agent skill. Fully open source.Introducing Anatomy
Describe a machine in one line. Claude brings it to life.
- Interactive isometric wireframes you can rotate, inspect and explore
- WebGL shaders for fire, water, plasma and more
- Real 3D motion, with individual parts that rotate and move
Install it as an agent skill. Fully open source.
Reinforcement learning is an important foundation for many domains.
I’m trying to learn, explore, and experiment with RL in biology.
RL can accelerate drug discovery, optimize treatment strategies, and improve biological experiments by learning which actions produce the best outcomes.Reinforcement learning is an important foundation for many domains.
I’m trying to learn, explore, and experiment with RL in biology.
RL can accelerate drug discovery, optimize treatment strategies, and improve biological experiments by learning which actions produce the best outcomes.
Build interactive visuals by connecting nodes, no coding required.
- Make 3D scenes and image effects
- Embed your work in other apps
- Extend it with custom plugins
Explore it here:
https://t.co/bxd26YcNqH https://t.co/c1mtowsPiiBuild interactive visuals by connecting nodes, no coding required.
- Make 3D scenes and image effects
- Embed your work in other apps
- Extend it with custom plugins
Explore it here:
https://t.co/bxd26YcNqH https://t.co/c1mtowsPii