Michiel Prins (@michielprins) 's Twitter Profile
Michiel Prins

@michielprins

Hacker. šŸ‘Øā€šŸ’» Runner. šŸƒā€ā™‚ļø Empowering the world to build a safer internet. ✨ Co-founder @Hacker0x01. šŸ¢

ID: 42017290

linkhttps://hackerone.com calendar_today23-05-2009 12:19:02

10,10K Tweet

9,9K Followers

992 Following

Ethiack (@ethiack) 's Twitter Profile Photo

Hackbots are here, now what? šŸ¤– AI-driven tools are changing how vulnerabilities are discovered, making security testing faster and more scalable. But automation alone isn’t the answer. As highlighted in HackerOne latest article, our CTO, AndrĆ© (AndrĆ© Baptista), emphasizes that the

Hackbots are here, now what? šŸ¤–

AI-driven tools are changing how vulnerabilities are discovered, making security testing faster and more scalable. But automation alone isn’t the answer. As highlighted in <a href="/Hacker0x01/">HackerOne</a> latest article, our CTO, AndrĆ© (<a href="/0xacb/">AndrĆ© Baptista</a>), emphasizes that the
Michiel Prins (@michielprins) 's Twitter Profile Photo

The power of collaboration and community. 24 hours and thousands of adversarial prompts later & no universal jailbreak uncovered yet.

Michiel Prins (@michielprins) 's Twitter Profile Photo

HackerOne is excited to partner this week with Anthropic on a brand new bug bounty challenge, leveraging the creativity of researchers to measure the resilience of the new Constitutional Classifiers system. Up to $30K in rewards for qualifying jailbreaks!

Jan Leike (@janleike) 's Twitter Profile Photo

Results of our jailbreaking challenge: After 5 days, >300,000 messages, and est. 3,700 collective hours our system got broken. In the end 4 users passed all levels, 1 found a universal jailbreak. We’re paying $55k in total to the winners. Thanks to everyone who participated!

Leonard Tang (@leonardtang_) 's Twitter Profile Photo

First came pre-training scaling; then came inference-time scaling. Now comes judge-time scaling. Despite progress in AI through scaled inference-time compute, AI remains unreliable in open-ended, non-verifiable domains. The key limitation is not generation—it is evaluation.

Michiel Prins (@michielprins) 's Twitter Profile Photo

$70K for an IDOR? Yep, it's possible! Snap is running a lucrative campaign in their public bug bounty program honing in on IDOR vulnerabilities. A crit can net you $70K! hackerone.com/snapchat?type=…

$70K for an IDOR? Yep, it's possible! Snap is running a lucrative campaign in their public bug bounty program honing in on IDOR vulnerabilities. A crit can net you $70K! hackerone.com/snapchat?type=…
Jobert Abma (@jobertabma) 's Twitter Profile Photo

.@HackerOne’s Hai can now visualize (complex) proof of concepts and it's magical! Understanding security vulnerabilities can be complicated, especially when reproducing it involves multiple accounts, many steps, or different systems — and this new Hai capability makes it so much

.@HackerOne’s Hai can now visualize (complex) proof of concepts and it's magical! Understanding security vulnerabilities can be complicated, especially when reproducing it involves multiple accounts, many steps, or different systems — and this new Hai capability makes it so much
Jobert Abma (@jobertabma) 's Twitter Profile Photo

.Caido and HackerOne are collaborating on a plugin that streamlines the H1 submission process. We’re envisioning a plugin that gives a simple UI to combine evidence that serves as the foundation of a report and removes most of the writing burden. Link in the comments.

Anthropic (@anthropicai) 's Twitter Profile Photo

We're launching a new bug bounty initiative to stress-test an updated version of our anti-jailbreaking system before it’s publicly deployed. The program, in partnership with HackerOne, runs through Sunday.