Logan Yang
@logancyang
Copilot for Obsidian | 👨💻 Building bicycle of the mind. e/ia youtube: loganhallucinates https://obsidiancopilot.com 🟩🟩🟩🟩🟩🟩🟩🟩⬜⬜(800k/1M downloads)
You might like
Copilot for @obsdmd won the best LLM integration 2024!!! 🔥🔥🔥 This community is amazing, thank you guys sooooo much for your support! ❤️🔥 And this is only the beginning. Please stay tuned for more in 2025! 😉
We've raised $100M from Kleiner Perkins, Index Ventures, Lightspeed, and NVIDIA. Today we're introducing Sonic-3 - the state-of-the-art model for realtime conversation. What makes Sonic-3 great: - Breakthrough naturalness - laughter and full emotional range - Lightning fast -…
Copilot for Obsidian reaches 800k downloads today! Can we hit 1M by end of year? Let's go!! 🚀🚀🚀
Great question! 1. CLI tools are not for everyone. Even some technical people prefer native GUI integration. We prioritize Obsidian native UI integration. 2. We want to create this portable infra for agents so people can run their agent with any capable model they can host…
People are suggesting notebookLM and LM studio in the comments but they are missing the entire point of what he's saying. Neither of them is sufficient for what Matthew is describing here. A private, portable AI agent infra is needed and we are building it.
📁 Matthew McConaughey says he wants a private LLM, fed only with his books, notes, journals, and aspirations, so he can ask it questions and get answers based solely on that information, without any outside influence.
We are in the process of building the UX for a privacy-focused agent around Obsidian into the Copilot plugin (one of the most downloaded AI plugins rn). The "file-over-app" philosophy but for AI agent. More to share soon.
Pro tip: for long multi-hour tasks, many of us at @OpenAI start by asking codex to write a markdown file with a plan and todos. Iterate on the plan then go!
GPT-5-Codex is relentless and runs until whatever you give it is really done.
- focus on things that bring you fulfillment and joy - delegate, automate, eliminate, and generally simplify - charge a lot more for your time
This new DeepMind research shows just how broken vector search is. Turns out some docs in your index are theoretically incapable of being retrieved by vector search, given a certain dimension count of the embedding. Plain old BM25 from 1994 outperforms it on recall. 1/4
I've had preview access to GPT-5 for a couple of weeks, so I have a lot to say about it. Here's my first post, focusing just on core characteristics, pricing (it's VERY competitively priced) and interesting details from the GPT-5 system card simonwillison.net/2025/Aug/7/gpt…
Introducing Kitten TTS, a SOTA tiny text-to-speech model - Just 15M parameters - Runs without a GPU - Model size less than 25 MB - Multiple high-quality voices - Ultra-fast - even runs on low-end edge devices Github and HF links below
9 out of the 10 fastest-growing LLMs this week are open-source
I'd like to point out that for the real world tasks (not benchmarks), Kimi K2 outperforms Gemini. This is telemetry across all @cline users, showing diff edit failure rate. Notice how Kimi has about a 6% failure rate, which is significantly better than Gemini's ~ 10% error…
Kimi K2 scored 59% on the aider polyglot coding benchmark. Full leaderboard: aider.chat/docs/leaderboa…
+1 for "context engineering" over "prompt engineering". People associate prompts with short task descriptions you'd give an LLM in your day-to-day use. When in every industrial-strength LLM app, context engineering is the delicate art and science of filling the context window…
I really like the term “context engineering” over prompt engineering. It describes the core skill better: the art of providing all the context for the task to be plausibly solvable by the LLM.
there doesn't have to be an end goal you can just make useful things for people who want to use them, and live a happy life
United States Trends
- 1. #BaddiesUSA 57.1K posts
- 2. Rams 29K posts
- 3. Scotty 9,573 posts
- 4. #TROLLBOY 1,891 posts
- 5. #LAShortnSweet 18.9K posts
- 6. Chip Kelly 8,425 posts
- 7. Cowboys 99.8K posts
- 8. Eagles 140K posts
- 9. Stafford 14.7K posts
- 10. Raiders 67K posts
- 11. Baker 20.9K posts
- 12. #ITWelcomeToDerry 14.7K posts
- 13. Bucs 12.2K posts
- 14. #RHOP 11.6K posts
- 15. Stacey 28.2K posts
- 16. Vin Diesel 1,145 posts
- 17. Ahna 6,794 posts
- 18. Teddy Bridgewater 1,211 posts
- 19. DOGE 165K posts
- 20. Todd Bowles 2,014 posts
You might like
-
matt palmer
@mattyp -
Robert Guss
@howtocode_io -
Nathan Fales
@NathanFales -
Finalz
@bubbleharth -
Bryan Fillmer
@bfillmer -
Andrew
@gratatouille23 -
Mateo Melgar
@mateomelgarcom -
Edmond Bitay
@edmondbitay -
Benoit Duchet
@duchetb -
Chris Elison
@ChristElison -
edmund
@kompuet -
Raggasensi🧢
@floyddarealmcoy -
Brooke Lea Wood
@brookeleawood -
Jessica J-Love
@JessicaJLove8 -
James A
@kiamesdavies
Something went wrong.
Something went wrong.