9/ LLM In-Context Recall is Prompt Dependent – finds that a model's recall performance is significantly affected by small changes in the prompt; the interplay between prompt content and training data can degrade the response quality.
AI
-

RAG Reduces Hallucination in LLM Structured Outputs
By
–
7/ Reducing Hallucination in Structured Outputs via RAG – shows that RAG can enable deploying powerful LLM-powered systems in limited-resource settings while mitigating issues like hallucination and increasing the reliability of outputs.
-

State-Space Models Express Power Limited to TC0 Complexity
By
–
6/ The Illusion of State in State-Space Models – investigates the expressive power of state space models (SSMs) and reveals that it is limited similar to transformers in that SSMs cannot express computation outside the complexity class 𝖳𝖢^0…
-
Chinchilla Scaling: Replication Attempt Challenges Hoffmann et al.
By
–
3/ Chinchilla Scaling: A replication attempt – attempts to replicate the third estimation procedure of the compute-optimal scaling law proposed in Hoffmann et al. (2022) (i.e., Chinchilla scaling); finds that “the reported estimates are inconsistent with their first two
-
Top ML Papers Week: Llama 3, Mixtral, RAG Advances
By
–
The Top ML Papers of the Week (April 15 – April 21): – Llama 3
– Mixtral 8x22B
– A Survey on RAG
– How Faithful are RAG Models?
– Emerging AI Agent Architectures
– Chinchilla Scaling: A replication attempt
… -
Llama 3 Family: 8B and 70B Models Released with Strong Performance
By
–
1/ Llama 3 – a family of LLMs that include 8B and 70B pretrained and instruction-tuned models; Llama 3 8B outperforms Gemma 7B and Mistral 7B Instruct; Llama 3 70 broadly outperforms Gemini Pro 1.5 and Claude 3 Sonnet.https://t.co/xqDJy0f0Vs
— DAIR.AI (@dair_ai) 21 avril 20241/ Llama 3 – a family of LLMs that include 8B and 70B pretrained and instruction-tuned models; Llama 3 8B outperforms Gemma 7B and Mistral 7B Instruct; Llama 3 70 broadly outperforms Gemini Pro 1.5 and Claude 3 Sonnet.
-
End-to-End Encryption Protects Only One Communication Element
By
–
Their end-to-end encryption is real, and a very good thing. But it only protects one element of your communications.
-
Comedy Channel Reaches 400k Subscribers with AI Content
By
–
A month later at 400k
— Andreas Klinger 🦾 (@andreasklinger) 21 avril 2024
Best new comedy right now
They are getting better with every videohttps://t.co/JHCJNrVjQV https://t.co/6IWUxOwea5A month later at 400k Best new comedy right now They are getting better with every video https://
youtube.com/watch?v=4Vf1j_
vnnMs
… -

Amazon’s Massive Investment in Alexa Development and Resources
By
–
I don’t think people realize the scale of the very largest tech companies & the resources they can deploy.
— Ethan Mollick (@emollick) 21 avril 2024
Amazon has spent between $20B & $43B on Alexa alone & has/had 10,000 people working on it. https://t.co/S0FBYmdVVyI don’t think people realize the scale of the very largest tech companies & the resources they can deploy. Amazon has spent between $20B & $43B on Alexa alone & has/had 10,000 people working on it.
-
Anticipating Code Interpreter Feature on Claude 3
By
–
Really looking forward to Code Interpreter on Claude 3
