To avoid the slot machine effect, differentiate between: —exploration time, where you’re playing with the AI and trying to learn how to use it properly, and —actual work time, where you have a specific objective to complete. Once you’ve hit your goal, close the AI.
TOOLS
-
Five Traps That Will Sabotage Your ChatGPT Efforts
By
–
5 traps that will sabotage your efforts with ChatGPT and similar tech:
-
Chatbots Connected to Search: Sparrow and Perplexity AI
By
–
E.g. our own Sparrow connects a chatbot to @Google search. A cool demo by @perplexity_ai shows something similar, and also allows you to query a @Twitter database for e.g. "histogram of top words from my tweets" (somehow I seem to use @ylecun a lot???).
-
LLMs With Tools: Beyond Single-Word Generation
By
–
Many people mistakenly think that large language models that generate one word at a time is the end game.
— Oriol Vinyals (@OriolVinyalsML) 11 janvier 2023
Connecting LLMs with tools, e.g.: search engines, python interpreters, etc., is super exciting, and leverages tools' power, robustness & more! pic.twitter.com/39PmdYEgwvMany people mistakenly think that large language models that generate one word at a time is the end game.
Connecting LLMs with tools, e.g.: search engines, python interpreters, etc., is super exciting, and leverages tools' power, robustness & more! -
Whisper Tutorial and VALL-E Accessibility Guide Available
By
–
Whisper tiene su tutorial (bastante sencillo) y notebook en el vídeo del canal. VALL-E por ahora no es accesible.
-
LangChain Multiple Memory Support Feature Release
By
–
Multiple Memory support – @diwanksingh You can now easily create a new memory instance that is a combination of multiple other types of memory! You no longer have to pick just one Documentation: https://
langchain.readthedocs.io/en/latest/modu
les/memory/examples/multiple_memory.html
… -
v0.0.60 Release: WolframAlpha Integration and Memory Support
By
–
v0.0.60 – big release! WolframAlpha integration – @nickscamara_ Multiple Memory support – @diwanksingh Doc improvements – @Yoooongtae Return scores during semantic search – h/t @krrish_dh Add namespaces to @pinecone – @m_morzywolek Deployment templates
-
Simplifying Complex Text: Key Concepts Extraction Technique
By
–
6. Simplify the complex When you want to rewrite a piece of text into a simpler, more accessible copy. Example use cases:
– Simplifying technical explanations
– Understanding complex text
– Extracting key concepts from a passage -
Condensing Information: A Key Prompt Engineering Technique
By
–
5. Condense information When you want to get a summarized version of a document that strips it to its essence. Example use cases:
– Summarizing reports
– Getting the TLDR of articles
– Generating the key points from a podcast