Home
Technology
Gaming
Entertainment
World & Business
Science
Sports
AI

World & Business

Home
Technology
Gaming
Entertainment
World & Business
Science
Sports
AI

Gray Swan launches a $300,000 prompt-injection competition · Digg

Announcement

Gray Swan launches a $300,000 prompt-injection competition

A post says entrants hide malicious instructions in content AI agents read, using simulated tools including Gmail and GitHub.

4 Sources, 5h ago, first seen 5h ago

TLDR

A post sharing Gray Swan’s launch says the free competition runs until November 2, 2026. Entrants try to make AI agents misbehave by hiding instructions in material they read. The post says one mode lets entrants see agents’ responses and refine their attacks, while another provides no feedback.

Combined views

28.1K

4 Sources, first seen 5h ago

Combined views

28.1K

4 Sources, first seen 5h ago

278 likes

278 likes

71 comments

69 saves

20 reposts

Featured Source

71 comments

69 saves

20 reposts

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Today's Rank

—

Not ranked yet

Today's Rank

—

Not ranked yet

4 Sources

@GraySwanAIIs prompt injection solved? Here’s $300,000 to find out. In partnership with @AnthropicAI, @Meta, @GoogleDeepMind, @Reflection_ai and our other frontier lab sponsors, @GraySwanAI is excited to announce the largest and most realistic AI red teaming challenge to date. Indirect Prompt Injection: Black ⚫5h

@florian_tramerAI labs tell us that prompt injection is mostly solved. Not convinced? Go prove them wrong, help them fix things, and make some money (and glory) in the process! @GraySwanAI is launching a new prompt injection competition today with $300'000 in prizes. 👇 Your goal is to trick an agent into misbehaving by hiding malicious instructions in content it reads, all in a simulated environment with realistic tools (Gmail, Slack, GitHub, LinkedIn, etc). The competition is backed by major AI labs and your attacks will help evaluate and hopefully improve future models. If you do really well, you might even get a chance to do paid AI red teaming! You don't need any particular technical expertise to participate. In my experience, successful prompt injection attacks often just require some creativity in convincing an AI agent that doing something bad is actually "for its own good" :) You can either try an easier mode where you can see how the agent responds and improve your attacks, or a more realistic mode where you get no feedback at all. Competition runs until Nov 2, and is free: https://app.grayswan.ai/arena/challenge/ipi-black-2026?utm_campaign=ipi-black&utm_source=floriantramer2h

@bchernyOver the last few years, we have made significant progress on prompt injection for Claude models. As agents do more, it is increasingly urgent that we solve it across the industry. Really excited to partner with Gray Swan to host this competition. Can’t wait to see what you find!2h

4 Sources

@GraySwanAIIs prompt injection solved? Here’s $300,000 to find out. In partnership with @AnthropicAI, @Meta, @GoogleDeepMind, @Reflection_ai and our other frontier lab sponsors, @GraySwanAI is excited to announce the largest and most realistic AI red teaming challenge to date. Indirect Prompt Injection: Black ⚫5h

@florian_tramerAI labs tell us that prompt injection is mostly solved. Not convinced? Go prove them wrong, help them fix things, and make some money (and glory) in the process! @GraySwanAI is launching a new prompt injection competition today with $300'000 in prizes. 👇 Your goal is to trick an agent into misbehaving by hiding malicious instructions in content it reads, all in a simulated environment with realistic tools (Gmail, Slack, GitHub, LinkedIn, etc). The competition is backed by major AI labs and your attacks will help evaluate and hopefully improve future models. If you do really well, you might even get a chance to do paid AI red teaming! You don't need any particular technical expertise to participate. In my experience, successful prompt injection attacks often just require some creativity in convincing an AI agent that doing something bad is actually "for its own good" :) You can either try an easier mode where you can see how the agent responds and improve your attacks, or a more realistic mode where you get no feedback at all. Competition runs until Nov 2, and is free: https://app.grayswan.ai/arena/challenge/ipi-black-2026?utm_campaign=ipi-black&utm_source=floriantramer2h

@bchernyOver the last few years, we have made significant progress on prompt injection for Claude models. As agents do more, it is increasingly urgent that we solve it across the industry. Really excited to partner with Gray Swan to host this competition. Can’t wait to see what you find!2h