Michael Becker (@beckerfuffle) 's Twitter Profile
Michael Becker

@beckerfuffle

Data Scientist @PennMedicine working to improve medicine by predicting the future! goo.gl/QV0G06. Also I started DataPhilly goo.gl/2epRg0. Amateur #AIArtist

ID: 1167666618

linkhttp://beckerfuffle.com calendar_today11-02-2013 03:09:03

4,4K Tweet

849 Followers

799 Following

LlamaIndex šŸ¦™ (@llama_index) 's Twitter Profile Photo

Introducing RAGApp šŸ’« A no-code interface to configure a RAG chatbot, as dead-simple as GPTs by OpenAI. It’s a docker container that’s easily deployable in any cloud infrastructure. Best of all, it’s fully open-source šŸ”„ 1ļøāƒ£ Setup the LLM: Configure the model provider (OpenAI,

Together AI (@togethercompute) 's Twitter Profile Photo

Mixture of Agents—a framework that leverages the collective strengths of multiple LLMs. Each layer contains multiple agents that refine responses using outputs from the preceding layer. Together MoA achieves a score of 65.1% on AlpacaEval 2.0. together.ai/blog/together-…

Mixture of Agents—a framework that leverages the collective strengths of multiple LLMs. Each layer contains multiple agents that refine responses using outputs from the preceding layer.
Together MoA achieves a score of 65.1% on AlpacaEval 2.0.
together.ai/blog/together-…
Eric Hartford (@cognitivecompai) 's Twitter Profile Photo

Cognitive Computations presents: Dolphin-2.9.3-qwen2-0.5b and Dolphin-2.9.3-qwen2-1.5b Two tiny Dolphins that still pack a punch! Run it on your wristwatch or your raspberry pi! We removed the coding, function calling, and multilingual, to let it focus on instruct and

Cognitive Computations presents:  Dolphin-2.9.3-qwen2-0.5b and Dolphin-2.9.3-qwen2-1.5b 
Two tiny Dolphins that still pack a punch!  Run it on your wristwatch or your raspberry pi!  We removed the coding, function calling, and multilingual, to let it focus on instruct and
Jeremy Howard (@jeremyphoward) 's Twitter Profile Photo

I've done a deep dive into SB 1047 over the last few weeks, and here's what you need to know: *Nobody* should be supporting this bill in its current state. It will *not* actually cover the largest models, nor will it actually protect open source. But it can be easily fixed!🧵

Alexandr Wang (@alexandr_wang) 's Twitter Profile Photo

We re-ran SEAL evals on the new Anthropic Claude 3.5 Sonnet model. It is now: - šŸ„‡ #1 on Instruction Following - šŸ„‡ #1 on Coding Congratulations to Anthropic on a great new model! P.S. we’re adding new evals to SEAL, so if you have an idea for an eval, let us know below šŸ‘‡

Travis Fischer (@transitive_bs) 's Twitter Profile Photo

pretty cool approach 1. use LLMs to extract a knowledge graph from your sources 2. cluster this graph into communities of related entities at diff levels of detail 3. for RAG, map over all communities to create "community answers" and reduce to create a final answer

Jonathan Ross (@jonathanross321) 's Twitter Profile Photo

What can you do with Llama quality and Groq speed? You can do Instant. That's what. Try Llama 3.1 8B for instant intelligence on groq.com.

Keith Sakata (@keithsakata) 's Twitter Profile Photo

I’m a psychiatrist. In 2025, I’ve seen 12 people hospitalized after losing touch with reality because of AI. Online, I’m seeing the same pattern. Here’s what ā€œAI psychosisā€ looks like, and why it’s spreading fast: 🧵

I’m a psychiatrist.

In 2025, I’ve seen 12 people hospitalized after losing touch with reality because of AI. Online, I’m seeing the same pattern.

Here’s what ā€œAI psychosisā€ looks like, and why it’s spreading fast: 🧵