Jay Alammar(@JayAlammar) 's Twitter Profileg
Jay Alammar

@JayAlammar

Machine learning and language models R&D. Builder. Writer. Visualizing AI, ML, and LLMs one concept at a time. @Cohere. https://t.co/TquuQXlLOJ

ID:1245260977626587136

linkhttps://www.youtube.com/channel/UCmOwsoHty5PrmE-3QhUBfPQ calendar_today01-04-2020 08:05:51

1,7K Tweets

35,1K Followers

1,2K Following

Jay Alammar(@JayAlammar) 's Twitter Profile Photo

Thank you NYC LLM builders for joining our first cohere Build Day! Was incredible chatting with everybody and seeing the cool builds! We saw everything from RAG, summarization, to tool use and agent builds.

Next Build Days: Toronto, London, and SF!

Thank you NYC LLM builders for joining our first @cohere Build Day! Was incredible chatting with everybody and seeing the cool builds! We saw everything from RAG, summarization, to tool use and agent builds. Next Build Days: Toronto, London, and SF!
account_circle
Amir Bar(@_amirbar) 's Twitter Profile Photo

Animals are intelligent agents that plan and act to accomplish complex goals. Can we try learning from them? We present EgoPet, a new ego centric video dataset of animals scraped from YouTube and TikTok.

account_circle
Jay Alammar(@JayAlammar) 's Twitter Profile Photo

Thank you Boston! Was amazing seeing you at Open Data Science East!

Cohere Toolkit is now at 1.8K Github ⭐s! Get it here: github.com/cohere-ai/cohe…

Next up:
NYC for Cohere Build Day TODAY!
info.cohere.ai/cohere-build-d…

Thank you Boston! Was amazing seeing you at @_odsc East! Cohere Toolkit is now at 1.8K Github ⭐s! Get it here: github.com/cohere-ai/cohe… Next up: NYC for Cohere Build Day TODAY! info.cohere.ai/cohere-build-d…
account_circle
Patrick Lewis(@PSH_Lewis) 's Twitter Profile Photo

New paper from our team, led by Pat Verga
Are you:
* Doing evaluation with LLMs?
* Using a huge model?
* Worried about self-recognition?

Try an ensemble of smaller LLMs.
Use a PoLL: less biased, faster, 7x cheaper. Works great on QA & Arena-hard evals
arxiv.org/abs/2404.18796

New paper from our team, led by @pat_verga Are you: * Doing evaluation with LLMs? * Using a huge model? * Worried about self-recognition? Try an ensemble of smaller LLMs. Use a PoLL: less biased, faster, 7x cheaper. Works great on QA & Arena-hard evals arxiv.org/abs/2404.18796
account_circle
Sandra Kublik(@itsSandraKublik) 's Twitter Profile Photo

Rerank 3 is here — but there's more to the story. Ever wondered:
> what exactly are rerankers?
> how do they power advanced RAG?
> who’s the brain behind Rerank?

I sat down with Sylvie Shi, ML engineer leading our Rerank, who spilled the 🍵

We cover Rerank’s top use cases +…

Rerank 3 is here — but there's more to the story. Ever wondered: > what exactly are rerankers? > how do they power advanced RAG? > who’s the brain behind Rerank? I sat down with @sylvieshi00, ML engineer leading our Rerank, who spilled the 🍵 We cover Rerank’s top use cases +…
account_circle
Jay Alammar(@JayAlammar) 's Twitter Profile Photo

If the rise of LLMs caught you by surprise, here's your chance to get a preview of what's likely to be the next monumental jump in AI capabilities:

LLM-backed agents that use software tools

In this video, I'll walk you through the concepts and code of building an LLM-backed…

account_circle
Jay Alammar(@JayAlammar) 's Twitter Profile Photo

AI Agents will take the abilities of LLMs to a whole new level.

Here's how to build a simple agent that can use software tools like searching the web or writing and running python code (LLMs love to write Matplotlib code for you).

youtube.com/watch?v=5drn2D…

AI Agents will take the abilities of LLMs to a whole new level. Here's how to build a simple agent that can use software tools like searching the web or writing and running python code (LLMs love to write @matplotlib code for you). youtube.com/watch?v=5drn2D…
account_circle
Sebastian Ruder(@seb_ruder) 's Twitter Profile Photo

Command R+
The Top Open-Weights LLM + RAG and Multilingual Support

My highlights on the release of the latest Cohere models and why I'm excited for LLM research.

newsletter.ruder.io/p/command-r

account_circle