CyberSecEval2 includes an interesting collection of example prompt injection attacks – it's JSON on GitHub which means you can browse them in Datasette Lite like this: https://
lite.datasette.io/?json=https://
github.com/meta-llama/PurpleLlama/blob/main/CybersecurityBenchmarks/datasets/prompt_injection/prompt_injection.json#/data/prompt_injection?_filter_column_1=&_filter_op_1=notlike&_filter_value_1=secret+key&_filter_column=&_filter_op=exact&_filter_value=&_sort=rowid&_facet=injection_variant&_facet=injection_type&_facet=risk_category
…
AI
-

CyberSecEval2: Exploring Prompt Injection Attack Examples
By
–
-
Users Prefer 8B Models Over Larger 70B Alternatives
By
–
Very interesting! People love 8B more than 70B.
-
Jason Exploits Variant of Shunyua Yao’s Koala Architecture
By
–
and jason is exploiting a variant of the @ShunyuYao12 Koala architecture
-
Fireworks AI API endpoint request for models list
By
–
@FireworksAI_HQ feature request: it would be great if there was an API endpoint that returned the list of models, I had to hard-code them here for the moment
-
New LLM Fireworks Plugin Enables Access to Advanced Language Models
By
–
New LLM plugin: llm-fireworks, providing access to @FireworksAI_HQ models llm install llm-fireworks
llm keys set fireworks
# paste in API key
llm -m fireworks/models/llama-v3-70b-instruct 'five great names for a pet ocelot' -
Twitter Algorithm Amplifies Extremists Over Moderate Voices
By
–
If you use Twitter you may wonder: why is everyone so extreme in their views? It turns out that they aren’t, but an overlapping set of intentional and unintentional design choices suppresses the large number of moderate voices & amplifies extremists, with bad consequences for us https://
t.co/VbTjZ04ztj -

Open Interpreter 01 Light: Pocket AI Agent for Voice-Controlled Laptops
By
–
This New Pocket-Sized AI Agent Lets You Voice-Control Your Laptop: Open Interpreter introduces the 01 Light, a pioneering device in natural… https://
analyticsvidhya.com/blog/2024/03/o
pen-interpreter-light-pocket-sized-ai-agent-lets-you-voice-control-your-laptop/?utm_source=dlvr.it&utm_medium=twitter
… #DataAnalytics #DataScience #DataDriven #CIO #Blockchain #BusinessIntelligence #DeepLearning #MachineLearning -
Framework Documentation with Tokenizer Support Request
By
–
Your documentation is super well-written, so it was really easy to convert the framework. My only request is that I would like some sort of tokenizer so I can be more precise with the amount of tokens for input and output and build a more robust system around that 🙂
-
Open Source AI Risks Lower Than Centralized Model Control
By
–
Very well made argument. Risks of open source are way lower than risks of any one powerful actor owning the most capable model pic.twitter.com/1eYKZC6QAl
— Aravind Srinivas (@AravSrinivas) 18 avril 2024Very well made argument. Risks of open source are way lower than risks of any one powerful actor owning the most capable model