7/ Evaluating Persona Agents – proposes a benchmark to evaluate persona agent capabilities in LLMs; finds that Claude 3.5 Sonnet only has a 2.97% relative improvement in PersonaScore compared to GPT 3.5 despite being a much more advanced model.
LLMS
-
ShieldGemma: LLM Safety Content Moderation Suite Built on Gemma
By
–
6/ ShieldGemma – offers a comprehensive suite of LLM-based safety content moderation models built on Gemma 2; includes classifiers for key harm types such as dangerous content, toxicity, hate speech, and more.
-
Improved RAG Self-Reasoning Framework for LLM Reliability
By
–
3/ Improved RAG with Self-Reasoning – presents an end-to-end self-reasoning framework to improve the reliability and traceability of RAG systems; leverages the reasoning trajectories generated by the LLM itself…
-
Constrained Chain-of-Thought Improves LLaMA2 Reasoning Accuracy
By
–
4/ Constrained-CoT – limits the model reasoning output length without sacrificing performance; shows that constraining the reasoning of LLaMA2-70b to 100 words improves the accuracy from 36.01% (CoT) to 41.07% (CCoT) on GSM8K, while reducing the average output length by 28 words.
-
Adaptive RAG for Conversation Systems: Gating and Confidence
By
–
5/ Adaptive RAG for Conversations Sytems – develops a gating model that predicts if a conversational system requires RAG to improve its responses; shows that RAG-based conversational systems have the potential to generate high-quality responses and high generation confidence.
-
Most Famous Generative AI Models Explained
By
–
What Is the Most Famous Generative AI? If you've been anywhere near the #internet in the past year, you've probably heard of #ChatGPT, #DALL-E, or perhaps #Midjourney. But what exactly is #GenerativeAI, and which model stands out as the most #famous?
-
ChatGPT Uses 10x More Electricity Than Google Search
By
–
There's a stat from the IEA cited in this Goldman Sachs report that says a ChatGPT query needs on average 10 around 10x more electricity than a Google search. https://
goldmansachs.com/intelligence/p
ages/AI-poised-to-drive-160-increase-in-power-demand.html
… -
Functional distinctions in AI model capabilities regarding internet access
By
–
Claude doesn’t have internet access, these are very different use cases
-
ChatGPT Becomes Popular Manifestation Tool Among TikTokers
By
–
People are now using ChatGPT as a #manifestation tool https://
businessinsider.com/tiktokers-usin
g-chatgpt-to-manifest-dreams-2024-8
… #LLM #LLMs #GenAI #GenerativeAI #OpenAI #ChatGPT #GPT #tech #AI #technology #artificalintelligence #Chatbot #MetaAI #llama31 #Llama3 #GROK -
Mapping Generative AI Misuse: Google DeepMind Analysis
By
–
Mapping the misuse of generative AI https://
deepmind.google/discover/blog/
mapping-the-misuse-of-generative-ai/
… #LLM #LLMs #GenAI #GenerativeAI #OpenAI #ChatGPT #GPT #tech #AI #technology #artificalintelligence #Chatbot #MetaAI #llama31 #Llama3 #GROK