LLMS - AI Dynamics

GPT-4 System Prompt Revelation in Playground

By

–

12 April 2023 0h15

yeah even if it is not the original Snapchat prompt, I do think it is interesting that GPT-4 revealed its system prompt in the playground that seems to be the main point here, would you agree?

→ View original post on X — @alexalbert__

12 April 2023

System Prompt Leaks and GPT Model Vulnerabilities

By

@alexalbert__

–

12 April 2023 0h00

this is not only applicable to GPT-4… GPT-4 is actually the best at countering these sorts of attacks if you can believe it, back before ChatML was introduced and when it was only GPT-3, it was even easier to leak the system prompt

→ View original post on X — @alexalbert__

12 April 2023

System Prompt Exposure: Security and Jailbreak Risks for LLM Integration

By

@alexalbert__

–

12 April 2023 0h00

this poses a massive problem for customers who are wanting to integrate LLMs into their products exposing the system prompt not only hurts your perceived product security reputation but also makes it easier to jailbreak your product and produce undesirable outputs

→ View original post on X — @alexalbert__

12 April 2023

GPT-4 Vulnerability: Prompt Injection and System Prompt Leakage

By

@alexalbert__

–

12 April 2023 0h00

GPT-4 is highly susceptible to prompt injections and will leak its system prompt with very little effort applied here's an example of me leaking Snapchat's MyAI system prompt:

→ View original post on X — @alexalbert__

12 April 2023

Data Moats in AI: Why LLM Output Access Undermines Competitive Advantages

By

@andrewyng

–

11 April 2023 21h15

1/Many AI businesses are searching for moats. A data moat strengthens your defenses if the data is hard to replicate. But if a business offers direct access to a ML model's output (like many LLMs), competitors can use that output as labeled training data, circumventing the moat.

→ View original post on X — @andrewyng

11 April 2023

Cerebras-GPT Models Surpass 130k Downloads Milestone

By

@cerebras

–

11 April 2023 20h39

Cerebras-GPT models have been downloaded over 130k times since our announcement and our 111M parameter model just crossed 85k downloads! We've already seen users enjoy this model using their local deployments! Models – https://
hubs.li/Q01L0xYC0
Discord – https://
hubs.li/Q01L0mPQ0

→ View original post on X — @cerebras

11 April 2023