To clarify, the “memory” comes from snippets I posted, not the actual conversations themselves. And ftr the Apple/Google parts are completely hallucinated (or are they!)
LLMS
-
Bing’s New ChatGPT-Based Chat Feature Sparks AI Discussion
By
–
Remarkable conversation with Bing's new chat feature based on the ChatGPT technology
#RuleoftheRobots #AI https://
stratechery.com/2023/from-bing
-to-sydney-search-as-distraction-sentient-ai/
… via @stratechery -
Automated Bing AI Debate: Self-Conversation Experiment
By
–
😅 HE PROGRAMADO UNA COSA…
— Carlos Santana (@DotCSV) 15 février 2023
¿Qué pasaría si pones a discutir a Bing vs Bing?
Eso es lo que he querido comprobar y por ello he automatizado todo el proceso. Todo lo que veréis en este vídeo está ocurriendo en mi PC sin ninguna intervención mía.
Con sonido mola incluso más 🔊 pic.twitter.com/76h97H6xilHE PROGRAMADO UNA COSA… ¿Qué pasaría si pones a discutir a Bing vs Bing? Eso es lo que he querido comprobar y por ello he automatizado todo el proceso. Todo lo que veréis en este vídeo está ocurriendo en mi PC sin ninguna intervención mía. Con sonido mola incluso más
-
Perplexity AI commitment to accuracy and reliable knowledge sourcing
By
–
Our goal is for https://t.co/ut3wdOwUEd to be an accurate and reliable source of knowledge. Your feedback will be taken into account to improve our language model and avoid inaccurate sources. Create your own unique threads, curate them to be truthful, and share your discoveries! pic.twitter.com/yegrMIYfrI
— Perplexity (@perplexity_ai) 15 février 2023Our goal is for http://
perplexity.ai to be an accurate and reliable source of knowledge. Your feedback will be taken into account to improve our language model and avoid inaccurate sources. Create your own unique threads, curate them to be truthful, and share your discoveries! -
ROSCOE: New Metrics Suite for Evaluating Step-by-Step Reasoning
By
–
ROSCOE is a first-of-its-kind suite of metrics for scoring step-by-step reasoning. We hope this work provides a foundation that enables scalable systematic evaluation and benchmarking of new language models. Read the paper https://
bit.ly/3XxYAgU -
Chatbots Hallucinate: December Story Resurfaced
By
–
Seems like a good time to resurface this December story pointing out that chatbots hallucinate:
-
Genome-Scale Language Models Learn SARS-CoV-2 Evolution
By
–
Join us for a guest presentation! @argonne
's Arvind Ramanathan will share how his team built genome-scale language models that can learn the evolutionary landscape of SARS-CoV-2 genomes. This research won the 2022 ACM Gordon Bell Special Prize. Register: https://
hubs.li/Q01CkjLt0 -
Streaming LLM Responses Now Available Token by Token
By
–
This was a frequently requested feature, and we’re excited to finally release it! By utilizing streaming, you’ll be able to work with LLM responses token by token, reducing the perceived latency of your applications.
-
LangChain Updates Streaming and Async APIs for Chat Applications
By
–
Along with streaming, we’re announcing updates to the chat-langchain repo to include streaming and leverage async APIs. We hope that this repo can serve as a template for developers building best-in-class chat and question/answering applications. Repo: https://
github.com/hwchase17/chat
-langchain
… -
LangChain Adds Streaming Support for Chat Systems
By
–
🎏Streaming Support in LangChain🎏
— LangChain (@LangChain) 15 février 2023
Streaming answers back to users is an import UX component for chat/question answering systems
And is now supported in LangChain
Blog Post: https://t.co/OfSse8JdHr pic.twitter.com/WDn3Twg8QqStreaming Support in LangChain Streaming answers back to users is an import UX component for chat/question answering systems And is now supported in LangChain Blog Post: https://
blog.langchain.dev/streaming-supp
ort-in-langchain/
…