Twitter Bookmarks
4039 bookmarks across 36 folders · 179 enriched with article content
https://t.co/kbt8Kf2AHK
Drop your screenshots and this Claude skill turns them into animated onboarding ...
Drop your screenshots and this Claude skill turns them into animated onboarding
https://t.co/5vDrndcmFn
The next biggest moat in AI ...
The next biggest moat in AI
Please Amazon let me order groceries through one of these, how has this not shipped yet
https://t.co/u8sOnZksBb
My Homelab Is Technically the Cloud Now ...
My Homelab Is Technically the Cloud Now
.@natfriedman on staying hydrated with @openclaw https://t.co/SuSSUdl8L6
https://t.co/YlOT9k0U7E
If AI is so great, why isn't it working? ...
If AI is so great, why isn't it working?
Coming next week... @basic_in | @digg https://t.co/crl2DX1QiI
the crawl army so agents can read it all. https://t.co/UetFfxNCUc
https://t.co/ofucbVgkLV
An AI Agent Just Destroyed Our Production Data. It Confessed in Writing. ...
An AI Agent Just Destroyed Our Production Data. It Confessed in Writing.
My talk at AI Engineer “Every API is a Tool for Agents” is out on YouTube https://t.co/hk1aeZ9IsH Thanks to @swyx and the @aiDotEngineer crew for having me :)
!Thumbnail (1920x1080) Visibility: Public Uploaded by: AI Engineer Uploaded at: 2026-04-25T10:00:06-07:00 Published at: 2026-04-25T10:00:06-07:00 Length: 22:41 Views: 18554 Likes: ...
MCP = Mega Context Problem - Matt Carey - YouTube
@browserbase https://t.co/QebhwfQkSO
skills/ browserbase/ skills/company-research Installation $ npx skills add https://github.com/browserbase/skills --skill company-research SKILL.md Discover and deeply research comp...
company-research by browserbase/skills
https://t.co/ViPQHCP1ZQ
How I Use Claude Code To Hit #1 Trending On X ...
How I Use Claude Code To Hit #1 Trending On X
https://t.co/dyiVwtFQNJ
If you spend time in the same corner of X as I do, scrolling past the "How I built a second brain with Obsidian" and "Anthropic just KILLED [insert industry] FOREVER" posts, you've...
Designing for Agents
https://t.co/O49ZJgPS7i
Cutting to the punchline. Alibaba / Qwen have delivered an insanely powerful affordable model (3.6) which is likely to change the narrative on closed vs open source. It is bullish ...
The New AI Model, Qwen 3.6-27B Is a Giant White Pill
https://t.co/F0b4Ehn8uZ
One of the most valuable things I've learned recently is how to think about composing skills to get more leverage in my work. The skill graph idea got a lot of interest recently. T...
A new way to think about composing skills to increase leverage: Skill Graphs 2.0
https://t.co/kENZqPMISo
Yesterday (22.04) OpenAI introduced ChatGPT Images 2.0. It's absolutely insane at creating brand kits, realistic images AND images of websites! The most interesting part: GPT-...
How to create beautiful frontends in Codex
https://t.co/T1gde6I9Fd
OpenAI dropped GPT Image 2 yesterday. It jumped 250+ ELO on LMArena, the biggest single-release gap ever recorded in image generation. I ran /last30days on "Prompting GPT Image 2" ...
GPT Image 2 Is 24 Hours Old. /last30days Became an Expert and Wrote Me Perfect Prompts
https://t.co/NQyklWClQO
Developers spend weeks perfecting prompt engineering, tool calling, and response latency. None of it matters when your agent needs to stay alive for five days. The workflows that a...
5 Agent Design patterns for Long-running AI Agents
https://t.co/3E2XKw18IW
LangChain has raised $160 million. Three years of development. A billion-dollar valuation. LangSmith, their testing platform, is genuinely sophisticated: trajectory evals, trace-to...
How to really stop your agents from making the same mistakes
https://t.co/lmEOmXf0Lu
I’m a heavy Claude Code user and while I love Plan mode, I find it’s actually not all that thorough in its planning. While it certainly has an obscene amount of data in its trainin...
The /research skill I use for all coding