Similar User
@repat123
@duetosymmetry
@jaceklaskowski
@iScienceLuvr
@CatJarman
@Jeande_d
@TartanLlama
@antinertia
@Ssil_crypto
@jasonbaldridge
@Gus_Nathan2024
@GratierR
@balijepalli
For like a decade I’ve struggled with different ways to save interesting papers, posts, etc I’ve found. The amount of time I actually look back at them is tiny. I’m considering abandoning it all and freeing myself. Am I an idiot?
LLM can now help me make code easier to understand and more scalable. It understands DRY principles better than I do.
The Chinese community is roaring. Nobody is sure how o1 is made in OpenAI and after @deepseek_ai and @AlibabaGroup here comes the third approach from @OpenMMLab ! Key takeaways: - small model distilled from large model CoT results - a combination of general and expert models
Foursquare just open sourced their 100 million place point of interest dataset! Some notes on poking around with it using DuckDB (it's Parquet files on S3) simonwillison.net/2024/Nov/20/fo…
I regret using @nextjs API routes. They take up 500MB for each PM2 cluster, I have 5 clusters, so they eat 2500MB RAM. ExpressJS, on the other, runs smoothly on just 50MB, and it's super reliable. Why did I think a frontend framework can do the job of a backend?
Now Qwen2.5-Turbo supports the context length of 1 million tokens! We demonstrate the performance on long text tasks and short text tasks both to show its effectiveness. To watch our demo, watch the videos in the replies. Feel free to try it out through our HF / Modelscope…
After the release of Qwen2.5, we heard the community’s demand for processing longer contexts. qwenlm.github.io/blog/qwen2.5-t… Today, we are proud to introduce the new Qwen2.5-Turbo version, which features: 📚 Longer Context Support: We have extended the model’s context length from…
LLLM can help me refactor code -- the key is to know what you are doing...
So excited to hear Nitro getting the recognition it deserves.. Try it! 🙏
We've been busy speeding up @duckdb queries in @definiteapp and one big lever has been DuckDB Server from @uwdata pick your poison: rust or python
📈 About the data science: 📈 We have identified topics of conversation using a topic modelling approach called BERTopic. We used sentiment analysis to identify the share of interactions that were positive, neutral or negative.
Neuromancer 1.5.2 is out! What is new: 1, Multi-fidelity Kolgomorov Arnold Networks for SOTA function approximation 2, Load forecasting on building energy systems tutorials 3, Transformer block github.com/pnnl/neuromanc… Thanks to the contributors and collaborators: Bruno Jacob,…
Here's a new lecture I made on learning embeddings with multidimensional scaling and TSNE for our ML course at Cornell Tech (with @volokuleshov). It covers the formulation and goes through some code for a deeper look Notebook: github.com/kuleshov/corne… PDF: drive.google.com/drive/folders/…
It’s wild to see the amount of growth that Python and TypeScript are experiencing
It's not just that Python is no. 1, but it's growth is still accelerating — it's also the fastest growing language! And (together with TS) Python is miles ahead of other languages in terms of growth.
I've been trying this one out via LLM and the llm-gguf plugin and it seems VERY impressive for its size Here's how to chat with the tiniest quantized version (just a 95MB file) llm install llm-gguf llm gguf download-model…
Introducing SmolLM2: the new, best, and open 1B-parameter language model. We trained smol models on up to 11T tokens of meticulously curated datasets. Fully open-source Apache 2.0 and we will release all the datasets and training scripts!
A few months ago, I wrote that the important thing about a database is how fast it is improving, not how fast it is today. Since then, MotherDuck has gotten 7x faster, according to ClickBench. We still have a lot of work to do, but not bad so far. motherduck.com/blog/perf-is-n…
United States Trends
- 1. Bengals 42,7 B posts
- 2. Kirk Cousins 8.729 posts
- 3. Steelers 54,5 B posts
- 4. Falcons 20,4 B posts
- 5. Colts 21,1 B posts
- 6. Trevor Lawrence 21,2 B posts
- 7. Seahawks 26 B posts
- 8. Penix 4.554 posts
- 9. Jets 46,6 B posts
- 10. #HereWeGo 7.939 posts
- 11. Pickens 16,3 B posts
- 12. Vikings 24,4 B posts
- 13. Anthony Richardson 3.098 posts
- 14. Russ 16,8 B posts
- 15. Texans 19,8 B posts
- 16. Drake Maye 5.256 posts
- 17. Cardinals 12,2 B posts
- 18. Titans 25 B posts
- 19. Jags 7.410 posts
- 20. #SKOL 4.403 posts
Who to follow
-
repat
@repat123 -
Leo C. Stein is @duetosymmetry on bsky/threads/🐘
@duetosymmetry -
Jacek Laskowski @[email protected]
@jaceklaskowski -
Tanishq Mathew Abraham, Ph.D.
@iScienceLuvr -
Prof Cat Jarman FSA💀
@CatJarman -
Jean de Nyandwi
@Jeande_d -
Sy Brand
@TartanLlama -
Jeddi
@antinertia -
𝑆𝑠𝑖𝑙 💎
@Ssil_crypto -
Jason Baldridge
@jasonbaldridge -
Gus Nathan
@Gus_Nathan2024 -
Romain Gratier
@GratierR -
Preetam.Balijepalli
@balijepalli
Something went wrong.
Something went wrong.