PhaseLLM v0.0.21 is out and come with support for Gemini. You can now plug-and-play and compare Gemini, GPT-*, and Llama 2.
Learn more: https://t.co/baeW5XDJsF
Code is all open source: https://t.co/Qfl2OLKrc7
#llms#gemini#geminiultra#genai#chatgpt#ai#ml
So cool -- our AI agents are crawling the web, looking at oil prices, and writing beautiful prose and analysis.
https://t.co/T288ZxxVZf
Current prediction? EOY oil prices at $85 USD per barrel.
#oil#finance#llms#gpt#ai#ml#economics
@gdb Very cool! We're exploring use of LLMs for "superforecasting" economic events, which requires a deep understanding of facts. This is one area/application that I think will really push LLMs to reason and uncover new knowledge.
It always blows my mind how much wider the partisan trust gap is for US media compared to the UK 🤯
Most British media is trusted (or distrusted) about equally by supporters of both major parties. That’s true of virtually no US media org.
Deeply corrosive for US society.
@nicolas94849298 Hello! Sorry for the delay. In short, YES!
We actually support the Hugging Face inference API and also Replicate for Llama 2. If you are looking for a specific API we can also help implement the wrapper.
We're releasing an experimental feature called "chained tables" for PhaseLLM Evals. This allows you to chain columns of data to test your prompts, reference variables, and build workflows.
Read more: https://t.co/JTh2ivoggg
#llms#gpt#chatgpt#openai#ai#ml#data#evals
Version 0.0.19 of PhaseLLM is out! We now have a seamless integration with https://t.co/pvpPoTPgb0 so you can log your chats and messages and have non-developers easily review them!
More updates below.
#llms#opensource#chatgpt#ai#ml#python#evals#data
PhaseLLM Evals: your copilot for prompt engineering, monitoring, and logging.
Our first hosted product, available today: https://t.co/6coNg1zJq4
Want to try it out? Let us know how we can help!
#llms#chatgpt#gpt4#ai#ml#stats#startups#nlp
PhaseLLM Evals: an MIT-licensed visual editor for running batch LLM jobs and evals
Demo video: https://t.co/GUesBNjd07
GitHub repo: https://t.co/K1Rx7lSpKE
#llms#evals#openai#gpt#chatgpt#ai#ml#data@openai
PhaseLLM version 0.0.18 is out! Live on PyPI and GitHub: https://t.co/Qfl2OLKrc7
This version has some minor changes and a *BIG* demo project that lets you run LLM evaluations visually. More info on *that* coming soon!
#llms#openai#chatgpt#ai#ml#evaluation#data
Do you analyze reports (SEC filings, ESG docs, etc.) and put them in a framework?
Soon our "Business Analyst LLM" will do that for you. 3-minute demo video here: https://t.co/pDCR1R9D0X
#mckinsey#bcg#bain#consulting#llms#chatgpt#ai#ml#analytics
MLAgentBench -- https://t.co/nzhXsXUrQh -- use LLMs to build ML models and improve those models
Really neat idea. Similar to ResearchLLM!
#researchllm#llms#chatgpt#ai#ml