Twitter’s algorithm is optimized for addiction, not for us. We deserve better.
We’re releasing Bouncer today so you can take back control of your feed. Describe what you don't want, and Bouncer removes it.
It’s free, doesn’t collect your data, and will be open source soon.
Haitian woman, 31, dies alone at Pittsburgh bus stop days after ICE released her to the streets far from home to perish. Rest in power, Daphy Michel: https://t.co/z3NLMTIjve
Sahli Negassi, a 17-year-old teen from West Orange, New Jersey scores a perfect 1600 on the SAT.
He plans to attend Harvard University and pursue a career in law 🔥
On a completely different channel, my personal apocalypse is so thick, my first thought was, "Of course it's $10k. I still can't do anything with this." But that's not what it said.
@alliekmiller@BobSummerwill I went to my first one today in Oakland/East Bay Area. 1 and 2… same. Also very few women and hushed ambivalence around how it affects life and humanity, possibly, etc. Thank you for sharing your observations, and thanks to Bob for resharing!
A new (to me) chat kept asking me to generalize about myself instead of asking how to explore my question. Chats might accelerate an undesirable filter-bubble effect if they generalize too early, via my prompting or on the backend.
That was my first time using CoPilot to investigate a new topic. It kept asking me to generalize about myself instead of asking how to explore my question. Chats might accelerate an undesirable filter-bubble effect if they generalize too early, via my prompting or on the backend.
"Library" has more than one definition. I love libraries!After last night's chat with CoPilot (it reminded me of things that I'd forgotten knowing), I'm glad to see that this library has the MIT License.
🚨 Microsoft just quietly dropped a tool that turns ANY document into LLM-ready data in seconds.
It's called MarkItDown, a lightweight Python library that converts PDFs, Word, Excel, PowerPoint, images, audio, and YouTube URLs into clean Markdown your LLM can actually use.
No custom parsers. No brittle pipelines. No preprocessing hell.
Built by the AutoGen team and battle-tested across 87K GitHub stars.
The numbers don't lie:
→ pip install markitdown and you're converting files in under 60 seconds
→ 10+ file formats supported out of the box
→ Native MCP server for direct Claude Desktop integration
And it works everywhere:
→ Command line: markitdown file.pdf > doc .md
→ Python API: 3 lines of code
→ Docker
→ Azure Document Intelligence for enterprise OCR
100% Opensource. MIT license.
This is the document preprocessing tool your RAG pipeline has been waiting for LLM-ready output without the LLM-ready headache.
Link in the first comment 👇
@zackbshapiro Hi Zack - I currently have access to https://t.co/4F2EeRuKBn. Please let me know if you or someone you know are interested in purchasing it! I can provide documentation and we can set up a call.