i think of them like LLMs
work great for glue-code tasks eg LLM's are great for stuff that's messy to code (eg get data from those random data dumps) eg agents are good for stuff that's messy to explain (eg search and figure out if person is X… i dont care which page)
LLMS
-
Agents vs LLMs: Comparing Use Cases and Applications
By
–
-
LLM AI boosts customer support productivity by 14 percent
By
–
Customer support productivity rises 14% with LLM AI tool! …with a 35% boost for the least experienced workers! https://
nber.org/digest/20236/m
easuring-productivity-impact-generative-ai
… -
Indigenous Languages Missing from LLM Development Discussions
By
–
As it is #NativeAmericanHeritageMonth I’d like to note that any discussion of @OpenAI or LLMs in general that doesn’t include how all indigenous (and other) languages will be included in any and all algorithms doesn’t honor vast portions of human culture, identity and rights.
-
New NLP Chair at Collège de France Begins Friday
By
–
"Teaching Languages to Machines": the Collège de France chair dedicated to NLP begins next Friday
-
AI Data Centers: Community Engagement for Water Protection
By
–
For instance, re the use of water & LLMs – imagine the joy & innovation that will come from any AI company reporting how their plans for new data centers were created via community engagement including indigenous populations to ensure water is protected for generations to come.
-
Web Grounding Reduces LLM Hallucinations in Knowledge Assistant
By
–
Model hallucinations are a big concern for organizations adopting LLM-based systems. This is why we’ve introduced a web grounding for Coral, our knowledge assistant. Watch NLP expert @itsSandraKublik demonstrate how it works. pic.twitter.com/4JLdMJEG7H
— Cohere (@cohere) 24 novembre 2023Model hallucinations are a big concern for organizations adopting LLM-based systems. This is why we’ve introduced a web grounding for Coral, our knowledge assistant. Watch NLP expert @itsSandraKublik demonstrate how it works.
-
Distil-Whisper: Hugging Face Releases New AI Model for Speed
By
–
Good morning fellow AI enthusiast! This week's iteration focuses on a big news from the @huggingface team releasing a new paper and model: Distil-Whisper. https://
open.substack.com/pub/louisbouch
ard/p/distil-whisper-enhanced-speed-and?r=25qlky&utm_campaign=post&utm_medium=web
… -
Model Hallucination Problem Will Be Solved Eventually
By
–
I am not saying model hallucination doesn't happen or that it's not a problem. But it will be solved one day.
-
LLM Hallucinations: Context Understanding and Grounding Reality
By
–
LLM hallucinations are different thing than human hallucinations. LLM is just missing the context, and because it’s a generative AI, it fills the gap. Future LLMs will be more aligned to understanding the context and they will be more grounded to reality, so they won’t