GPT wrapper apps are exactly the things that need to worry about prompt injection – it's not an attack against the models, it's an attack against applications built on top of the models
TOOLS
-
Logitech’s AI Ease Problem: Synthetic Information Overload
By
–
"Gen AI" is sold as making things easy ("produce art", "write novels" etc). So it's telling to see Logitech doubling down on making it even easier. We aren't dispensing enough of the synthetic info? Maybe the problem isn't that it takes too many clicks.
-
Community Builds Amazing Datasets with distilabel 1.0
By
–
Very excited to see all the amazing datasets the community builds and shares on the Hub using distilabel 1.0!
-
OAuth OpenAI Integration for Billing and Prompt Execution
By
–
This is for me being bills and knowing how much to charge them later A separate thing I'd love is the ability to oauth against their OpenAI account to gain the ability to run prompts on their behalf
-
OpenAI Updates Kill Startups While RAG Becomes Standard
By
–
Every OpenAI product update kills a bunch of startups & expensive consulting projects. RAG is increasingly being built into core AI model offerings (but RAG is quite limited, and, at times, risky. See halfway though this post: https://
oneusefulthing.org/p/which-ai-sho
uld-i-use-superpowers
…) -
Assistants API Updates: Expanded File Support and Better Control
By
–
Launching a series of updates to the Assistants API—now with support for up to 10,000 files for knowledge retrieval and more precise tool and token control. Excited to see what you build!
-
LangSmith Evaluations: Unit Tests for LLM Development
By
–
LangSmith Evaluations: Unit Tests
— LangChain (@LangChain) 17 avril 2024
Evaluations can accelerate LLM app development, but it can be challenging to get started. We've kicked off a new video series focused on evaluations in LangSmith.
This is the 10th video in our series that shows how to incorporate unit… pic.twitter.com/nSd8CiuAdRLangSmith Evaluations: Unit Tests Evaluations can accelerate LLM app development, but it can be challenging to get started. We've kicked off a new video series focused on evaluations in LangSmith. This is the 10th video in our series that shows how to incorporate unit
-
LangChain adds token usage tracking for LLM responses
By
–
Token usage tracking We've made it easier to access response metadata returned by LLM providers with a new field on AIMessages! Useful information like token usage for supported models will appear there. Python : https://
python.langchain.com/docs/modules/m
odel_io/chat/token_usage_tracking/
…
JS : https://
js.langchain.com/docs/modules/m
odel_io/chat/token_usage_tracking
… -
Stability API Documentation Download Feature for LLM Implementation
By
–
I love how the new Stability API page has a button to download the entire specification. Easiest way to feed it to an LLM for quick implementation and testing. Every documentation page should have this.
-
Claude 3 Opus prompt result on Poe impresses user
By
–
Just ran a prompt on Claude 3 Opus via Poe . com and this popped up. Love to see it.