Benchmarks look really good… congrats @erhartford
!
LLMS
-
Strong AI Benchmarks Achievement Recognized
By
–
-
OpenAI Finally Addresses Prompt Injection and Jailbreak Taxonomy
By
–
interesting that 1.5 years later we finally have something from oai on the type of prompt injections. I called jailbreaks "takeovers" back then. https://
buttondown.email/ainews/archive
/ainews-openai-reveals-its-instruction-hierarchy/
… -
Follow AI Blogs in 2024 for ChatGPT Updates, Skills, Networking
By
–
Follow AI Blogs in 2024 Stay ahead in tech and innovation • Track ChatGPT updates
• Enhance AI skills
• Expand networking Read more: https://
godofprompt.ai/blog/chatgpt-f
ocused-blogs-to-follow-in-2024
… -
GradCache Optimization for Distributed GPU Training
By
–
oh yeah. I think his trick was just GradCache. and sharing negatives between GPUs isn’t trivial
-
Llama-2 Improves Game Performance Through Adversarial Self-Play
By
–
This is worth noting: it appears to be the first evidence that LLMs can improve performance at a task through self-play. In this case, Llama-2 7B was able to greatly improve its ability to play the game of Adversarial Taboo by training through adversarial competition with itself
-
Snorkel Flow Enables Custom LLM Deployment Enterprise Data
By
–
We are excited to announce a new release of Snorkel Flow, empowering enterprises to programmatically and securely customize LLMs using their own multi-modal data. Learn more about how Snorkel Flow can help you harness the power of custom LLM's: https://
buff.ly/4de08WA -
Code Interpreters: The Bicycle of LLM Mind with LangChain
By
–
We're really excited about code interpreters. They're the bicycle of the (LLM) mind Come see how to use @e2b_dev's code interpreter with LangChain and bounce ideas with other builders!
-
Command R and Command R+ Now Available on Poe Platform
By
–
Command R is accessible at https://
poe.com/Command-R and Command R+ is at https://
poe.com/Command-R-Plus. Both bots are also available across all Poe apps. (2/2) -
Cohere Command R and R+ Models Now Available on Poe
By
–
Now on Poe: Command R and Command R+ from Cohere! These bots excel at understanding complex questions and long conversations, providing detailed answers in over 10 languages. They can also search the web for the latest information to enhance their responses. (1/2)
-
LLMs Intelligence: Argument Evaluation and Personalized Appeal Prediction
By
–
LLMs are already pretty intelligent; they can distinguish between strong and weak arguments, predict stances based on beliefs and demographic characteristics, and determine the appeal of an argument to an individual based on their traits. The paper below shows that LLMs perform