PSA: Don’t run eval() on LLM-generated code outside of a sandbox VM, especially if you’re generating code with untrusted user input in the prompt.
LLMS
-
ChatGPT Revolutionizing Healthcare with Accurate Medical Answers
By
–
Revolutionizing #healthcare with #ChatGPT #technology : Providing accurate & efficient answers to medical questions, improving patient outcomes & overall experience #Health #OpenAI #FutureOfMedicine #FutureOfWork
-
GPT-3 enables businesses to query their own data via Channel beta
By
–
Businesses will soon be able to use GPT-3 to ask questions about their own data.
— AI Breakfast (@AiBreakfast) 29 janvier 2023
Channel is currently in beta – expect this to be huge.https://t.co/BIYic9ZKf2 pic.twitter.com/5xUVli05eOBusinesses will soon be able to use GPT-3 to ask questions about their own data. Channel is currently in beta – expect this to be huge. https://
usechannel.com -
Video on the dark side of ChatGPT and AI models
By
–
online! The (very) dark side of #chatGPT. Deep dive into the heart of #ArtificialIntelligence models. The video from the channel I'm most proud of. Thank you in advance for your support through your shares, likes, comments
-
LangChain Updates: Context Windows, Cohere Support, Bug Fixes
By
–
Other improvements: – Correct context window for davinci-003 :
@wskish – Docs improvements: wunderalbert
– Fix bash util: h/t Marcin in discord
– Add support for arbitrary params to Cohere wrapper: h/t bair82 in discord
– Fix caching bug: @brucehammer -
LangChain Search Classes Enhanced with Detailed Metadata Results
By
–
More detailed search results @EnricoShippole added a method to the search classes to return more detailed search info: title, snippet, link WebGPT? Google Search: https://
langchain.readthedocs.io/en/latest/modu
les/utils/examples/google_search.html#metadata-results
… Bing Search: https://
langchain.readthedocs.io/en/latest/modu
les/utils/examples/bing_search.html#metadata-results
… -
GPU Support Added for Hugging Face Models in LangChain
By
–
Support for GPUs with @huggingface models Thanks to @parth_29 you can now more easily use GPUs for huggingface pipelines! PR here: https://
github.com/hwchase17/lang
chain/pull/750
… -
Major Software Release: GPU Support and Tool Decorator Features
By
–
Big weekend release! Too many changes to even try to list in a single tweet But as a teaser: – Support for using GPUs with @huggingface models
– A decorator to easily turn a function into a Tool
– Lots more! -
Learning Prompt Engineering: Essential Guide and Resources
By
–
Interested in learning more about prompt engineering, check out – https://
learnprompting.org -
ProGen: LLM Generates Protein Sequences with Predictable Function
By
–
ProGen – an LLM that can generate protein sequences with a predictable function across large protein families. 10 of 11