Unlikely to happen with proprietary systems because they probably think of their prompts as trade secrets (though they'll leak easily enough to anyone who tries to get them), but open source AI assistants would have less incentive to try and hide their implementation details
LLMS
-
OpenAI adds vision to ChatGPT on iOS
By
–
BREAKING : OpenAI is planning to add vision capabilities to the conversation mode of ChatGPT on iOS! This feature will allow you to take a picture or upload any photo while you are in conversational mode
-
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
-
AI Summarizer Bot Integrated Into Text Messages
By
–
I made myself an insanely useful AI summarizer bot.
— Matt Shumer (@mattshumer_) 27 avril 2024
It lives in my text messages.
I just send it a link to an article, video, etc., and it texts me back a fantastic summary, in seconds.
This is going to be a massive time-saver. pic.twitter.com/bEw7Dej2NpI made myself an insanely useful AI summarizer bot. It lives in my text messages. I just send it a link to an article, video, etc., and it texts me back a fantastic summary, in seconds. This is going to be a massive time-saver.
-
LLMs excel at providing problem-solving frameworks
By
–
A valuable thing that teachers and coaches do is provide frameworks for solving problems. LLMs are very good at frameworks: they "know" a lot of them, and they are excellent at applying them to your problem. Here's a little GPT that suggests & makes them: https://
chat.openai.com/g/g-vZ7SgKBOh-
framework-finder
… -
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
… -
Defining AI Agents: Code Interpreter as Goal-Achieving LLM
By
–
(depending of course on which definition of "agent" you like to use! I'm using Code Interpreter as an example of an LLM that runs in a loop trying to achieve a goal across several attempts, using an external tool)
-
Engineering LLM Systems with External Tools for Reliability
By
–
But in a well-engineered system that provides access to tools, runs searches against external systems, then feeds those results back into the LLM as part of the context supplied alongside the prompt: the reliability shoots up enormously… but there will still be weird edge-cases
-
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!