Earth Month may be wrapping up, but our mission continues. Check out how tech meets climate research for a sustainable future. http://
spr.ly/6011b0XBW #EarthMonth #SustainableEnergy #ClimateAction
RESEARCH
-
Tech Meets Climate Research for Sustainable Future
By
–
-
Conditioning and In-Context Learning: Architecture’s Impact Analysis
By
–
what i am confused that more people dont seem to be analysing is how does the conditioning improve (or not) with increasing attention heads and layers. i dont know if anyone is formally quantifying amount of conditioning/ICL as an explicit loss function/training goal. in other
-
Evaluating Small Models Beyond MMLU: Tool Use and Summarization
By
–
MMLU tests mainly for knowledge, which doesn't make much sense for smaller models – I'm more interested in how good it is at tool use, summarization, fact extraction etc – I've not figured out the best commonly reported benchmark for that yet though
-
Al-Khwarizmi: The Mathematician Behind Computing History
By
–
al-Khwarizmi! Such a fascinating story.
-
Developer Takes Synthetic Data Break with Quick Refresh Build
By
–
Spending the day thinking about synthetic data but I need a break. I think it’s time for a tiny refresh build to reset my mind. Aiming to get something done within an hour. Will post the result.
-
AutoHyDE: Advanced RAG Technique for LLM Enhancement
By
–
AutoHyDE: Making HyDE Better for Advanced LLM RAG A fun article exploring new and creative RAG techniques Builds upon HyDE to add in keyword generation, clustering, etc Implements a LangChain Embedder which makes it easy to try out in your pipeline https://
towardsdatascience.com/autohyde-makin
g-hyde-better-for-advanced-llm-rag-619e58cdbd8e
… -
Can You Trust LLMs to Tell the Truth?
By
–
"Can I trust LLM AI to tell me the truth?" is such an interesting question Short answer: no, but it varies depending on the context Expecting it to tell the truth based on its weird opaque blob of matrices derived from its original training data is very risky indeed
-
Different Architecture and Pre-trained Model Approach
By
–
it's a very different architecture and starting from a different pre-trained model!
-
LazyClassifier for Classification Problems Usage Guide
By
–
Similarly here is using LazyClassifier for Classification Problems. Check this out:
-
Can Orange Line Catch Blue Line Without Waiting?
By
–
POLL: is the orange line going to catch up to the blue line? is there any way to know without just waiting? (it will take 5 days) this feels like the Halting Problem