You might like
After a year of quietly powering some of the best restaurants, we’re finally introducing Magic — the personalization engine for real world experiences. Our first product, Loyalist, is live in hundreds of restaurants in 40+ cities like CARBONE, Momofuku, Le Bernardin, and COTE.
...is it sacrilege to run a Deep Research query and then ask for a summary
sometimes feel like we're still in 2023... guys your enterprise product still has to solve a real problem even if it uses AI
Debating the morals of saying "thank you" to LLMs after a good job. Pros - kind, possibly gains favor in AI uprising Cons - extra energy use
No matter what you do in life, this paper is a must read. It's short and easy to follow.
This paper from Meta proposes a method to not have the model reason in token space but directly model its reasoning using its hidden state. The authors also do a lot of cool interpretability work in this paper. Aesthetically, I like it alot and its simple to implement
Coming back to an area I used to track closely - What are the best services / approaches for complex tables and AI? I'm focused particularly on data ingestion and normalization but would love to hear of services / approaches relevant to downstream tasks (e.g. reasoning).
This election is going to change our country forever. Life will get complicated, noise will be everywhere. But HF0 will be quiet. It’s where ten teams will be shutting out the world to build generational companies. Applications open today: hf0.com (1/5)
1300+ tok/s on a MacBook implemented batched KV caching in MLX for fast parallel LLM inference on Apple devices. can get over 20x tok/s throughput gains depending on model/precision/RAM/batch size. screenshot is for Gemma-2B in float16 + 325 prompts in the batch code:…
been learning a lot about LLMs etc over the past year, organized some of my favorite explainers into a “textbook-shaped” resource guide wish i’d had this at the start, maybe it can useful to others on a similar journey genai-handbook.github.io
Volatility drag is not real. Long live Nepers. Some of the world’s largest asset managers meaningfully adjust their investment policies to reduce volatility drag. What is volatility drag? When you model asset returns as geometric brownian motion with arithmetic mean % return μ…
United States Trends
- 1. #WorldSeries 116K posts
- 2. Ernie Clement 8,341 posts
- 3. #SNME 75.7K posts
- 4. Hugh Freeze 3,387 posts
- 5. Auburn 10.2K posts
- 6. Ohtani 59.3K posts
- 7. Blue Jays 72.8K posts
- 8. Gimenez 14.6K posts
- 9. Bo Bichette 24K posts
- 10. Jesse Love 3,382 posts
- 11. Mateer 2,770 posts
- 12. Tate Sandell N/A
- 13. Max Muncy 2,886 posts
- 14. Jordan Marshall 1,377 posts
- 15. Nebraska 12.9K posts
- 16. Toronto 47.5K posts
- 17. NC State 3,428 posts
- 18. Heupel 1,107 posts
- 19. Zilisch 5,290 posts
- 20. Shohei 41.3K posts
You might like
-
ethan ding 📊
@TheEthanDing -
Nouf
@noufalsoghyar -
Advait Maybhate
@AdvaitMaybhate -
Ryan Chang
@ryancwc_ -
Ally
@allywaytalk -
Chandler Rogers
@chandlerr1313 -
Nikhil Gupta
@nikhilro_ -
Madison Frye
@madisonafrye -
Anthony Parente
@aparente__ -
Adit
@aditabrm -
alexis ♡
@itsalexiswei -
Brooke Presten
@brookepresten -
Leyton
@leytonho -
alexis wiseman
@alexisajwiseman -
sarbo
@notsarbo
Something went wrong.
Something went wrong.