LLMS - AI Dynamics

Comprehensive Prompt Engineering Guide with References

By

–

13 January 2023 15h42

Prompt Engineering Guide (1.1K) This new guide helps you find the latest & greatest information regarding prompt engineering. More references were added. Lecture + notebook coming soon! https://
github.com/dair-ai/Prompt
-Engineering-Guide
…

→ View original post on X — @dair_ai

13 January 2023

LangChain OutputParsers: Formatting LLM Outputs and Error Handling

By

@langchain

–

13 January 2023 6h41

its under documented, but checkout things like our OutputParsers – https://
github.com/hwchase17/lang
chain/blob/3e55f1474e5ad13f90c233b7f85480e996765e71/langchain/prompts/base.py#L67
… they can parse an LLM output into a specific format. however, it is an open question about what to do if format is not expected… retry?

→ View original post on X — @langchain

13 January 2023

Inferring Context Size from Model Parameters

By

@swyx

–

13 January 2023 2h13

oh. then i was a bit misled by the landing page infer the context size from the model. theres not that many to do and you make it a bit more magical

→ View original post on X — @swyx

13 January 2023

Strategies for Overcoming Context Length Limitations in Language Models

By

@swyx

–

13 January 2023 1h40

interesting. how do you get around context length limits? do you use langchain? (which just kinda kicks the can down the road)

→ View original post on X — @swyx

13 January 2023

DeepMind CEO hints at 2023 Sparrow beta release citing sources

By

@aibreakfast

–

13 January 2023 1h37

CEO of Google's DeepMind @demishassabis hinted today at a 2023 private beta release of "Sparrow" (DeepMind's version of ChatGPT) that will be capable of citing sources for its responses.

→ View original post on X — @aibreakfast

13 January 2023

GPT-4 capabilities and Microsoft’s AI strategy revealed

By

@cademetz

–

13 January 2023 0h24

Some VCs and Microsoft employees have already seen GPT-4. It could be text only, like ChatGPT. Or it could include images. OpenAI has not decided which to release, @KYWeise and I report in our piece on Microsoft's return to the center of the tech universe:

→ View original post on X — @cademetz

13 January 2023

Abacus AI Launches Foundation Models for Language Vision Speech

By

@abacusai

–

12 January 2023 23h00

You can now integrate generative models into your system using Abacus AI! We have m foundational models: language, vision, and speech. You can fine-tune them and start using them right away! https://
abacus.ai/foundation_mod
els
…

→ View original post on X — @abacusai

12 January 2023