computers and things that go fast. https://teapaw.org/t.co/fjywy59vmd _ 300k+ people kensaku ⭐ 1.4k+ https://teapaw.org/t.co/zxOlYe8rI9 _ AI editing videos ex-eng photogpt
root@earth-616
Joined August 2024
- Tweets1.3K
- Following561
- Followers732
- Likes2.8K
Pinned Tweet
-10 degree in just few seconds is crazy cool.
But where is the use of AI in this ?? . Can anyone tell me 🥶
Yash J. retweeted
Search your files by what's in them, not their name.
Kensaku is an open-source desktop search app that reads inside your files and runs locally.
→ Full text across PDF, DOCX, EPUB and more
→ OCR for text inside screenshots
→ Find by meaning, not just keywords
→ MCP, so agents can search the same index
Useful if you keep losing files with bad names.
Quick start: installers for Windows, macOS and Linux on the releases page
800 stars, MIT (5 Nov). By @imgochi
github.com/yjid/kensaku
ALT Two Kensaku app windows over a wallpaper of sky and trees: a dark splash screen reading "found it" in Japanese and English, and a light search window listing recent docx, md and txt files.
This fr is crazy . 🤯
Z.ai chief scientist Jie Tang just revealed the training pipeline behind the upcoming GLM-5.5 (32B, 122B, and 256B) during a lecture at Tsinghua University today.
Instead of relying on public datasets, their pretraining pipeline pulls from six separate internal engines:
- Web: 1 trillion pages crawled at ~10B pages/day with PB-scale template clustering
- Documents: 2 billion scientific PDFs parsed through GLM-OCR (4x faster with speculative decoding)
- Books: 50 million books with layout reordering and garbled-text filtering
- Code: 500 million repositories turned into executable tasks with real tests and issue descriptions
- Video: 10 billion videos for long-sequence world knowledge
- Audio: 300 million hours rewritten via ASR into trillions of tokens
BRO I JUST GOT HERE. I'M NOT DYING.
1,000+ GITHUB STARS.🚀
Built Kensaku because finding files on my own computer was painful.
Now 1,000+ people have starred this little project.
Local semantic file search. PDFs, documents, filenames, OCR. No cloud. No bullshit.
⭐ github.com/yjid/kensaku
1,000+ GITHUB STARS.🚀
Built Kensaku because finding files on my own computer was painful.
Now 1,000+ people have starred this little project.
Local semantic file search. PDFs, documents, filenames, OCR. No cloud. No bullshit.
⭐ github.com/yjid/kensaku
I have 3 projects still in development and just 15 days to ship before GTA 6. 😖😖😖 The last 4 days have been too much college & travelling. Low efficiency
Yash J. retweeted
We were promised universal basic income. RAM Altman gave us feudalism with API keys.
