"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis

Exploitable by Default: Vulnerabilities in GPT-4 APIs and “Superhuman” Go AIs with Adam Gleave of Far.ai

17 snips

Mar 27, 2024

In a captivating discussion, Adam Gleave, founder of Far AI and expert in AI exploitability, delves into the vulnerabilities of GPT-4 and superhuman Go AIs. He reveals how naive fine-tuning can create exploitable flaws, leading to serious cybersecurity risks. The conversation also touches on the ethical implications of disclosing these weaknesses and the critical need for robust safety measures in AI development. Gleave highlights the balance needed between enhancing AI performance and maintaining security, making for an enlightening exploration of AI's future challenges.

Ask episode

AI Snips

Chapters

Transcript

Episode notes

INSIGHT

Accessibility of AI-powered Attacks

AI-powered attacks are concerning because they increase the scale and accessibility of malicious activities.
This changes the economics of attacks, potentially empowering both attackers and defenders.

INSIGHT

Future Implications of AI Exploits

Current AI capabilities are already concerning, but future, more advanced models will be even more so.
The trend of increasing model capabilities without corresponding improvements in robustness is worrisome.

ANECDOTE

Accidental Jailbreaking

Adam Gleave's team accidentally removed safety filters on GPT-4 during fine-tuning.
Fine-tuning on benign data can reverse safety training, highlighting its fragility.

Get the Snipd Podcast app to discover more snips from this episode

Get the app

In this episode, Nathan sits down with Adam Gleave, founder of Far AI, for a masterclass on AI exploitability. They dissect Adam's findings on vulnerabilities in GPT-4's fine-tuning and Assistant PIs, Far AI's work exposing exploitable flaws in "superhuman" Go AIs through innovative adversarial strategies, accidental jailbreaking by naive developers during fine-tuning, and more. Try the Brave search API for free for up to 2000 queries per month at https://brave.com/api

RECOMMENDED PODCAST: Autopilot explores the adoption and rollout of AI in the industries that drive the economy and the dynamic founders bringing rapid change to slow-moving industries. From law, to hardware, to aviation, Will Summerlin interviews founders backed by Benchmark, Greylock, and more to learn how they're automating at the frontiers in entrenched industries.

Listen on Spotify: https://open.spotify.com/show/6YQZkKHN7EP2yWedAvSxBC?si=18377c69a2804333

Listen on Apple: https://podcasts.apple.com/ca/podcast/autopilot-with-will-summerlin/id1738163836LINKS:

LINKS:

Far AI: https://far.ai/author/adam-gleave/

X/SOCIAL:

@labenz (Nathan)

@ARGleave (Adam)

@FARAIResearch (Far.AI)

SPONSORS:

Oracle Cloud Infrastructure (OCI) is a single platform for your infrastructure, database, application development, and AI needs. OCI has four to eight times the bandwidth of other clouds; offers one consistent price, and nobody does data better than Oracle. If you want to do more and spend less, take a free test drive of OCI at https://oracle.com/cognitive

Omneky is an omnichannel creative generation platform that lets you launch hundreds of thousands of ad iterations that actually work customized across all platforms, with a click of a button. Omneky combines generative AI and real-time advertising data. Mention "Cog Rev" for 10% off www.omneky.com

The Brave search API can be used to assemble a data set to train your AI models and help with retrieval augmentation at the time of inference. All while remaining affordable with developer first pricing, integrating the Brave search API into your workflow translates to more ethical data sourcing and more human representative data sets. Try the Brave search API for free for up to 2000 queries per month at https://brave.com/api

ODF is where top founders get their start. Apply to join the next cohort and go from idea to conviction-fast. ODF has helped over 1000 companies like Traba, Levels and Finch get their start. Is it your turn? Go to http://beondeck.com/revolution to learn more.

💥 Access global engineering without the headache and at a fraction of the cost: head to choosesquad.com and mention “Turpentine” to skip the waitlist.

TIMESTAMPS:

(00:00:00) Episode Preview

(00:01:25) The alarming reality of AI exploits: from accidental jailbreaking to malicious attacks.

(00:16:45) The Assistants API: a new frontier for AI exploitation.

(00:41:54) The ethical dilemma of AI security research and disclosure.

(00:51:36) Exploring AI vulnerabilities: a deep dive into GPT-4's exploits.

(00:51:47) The challenge of AI robustness and the 'Accidental Jailbreaking' phenomenon.

(00:52:39) Navigating the Assistants API: security risks and malicious exploits.

(00:53:27) The robustness tax: balancing AI safety with performance.

(01:07:42) Unveiling flaws in superhuman Go-playing AIs: a gray-box investigation.

(01:36:50) Empirical scaling laws for adversarial robustness: a future focus.

(01:41:53) Closing remarks and opportunities at FAR AI

The Cognitive Revolution is produced by Turpentine: a media network covering technology, business, and culture.

Producer: Vivian Meng

Editor: Graham Bessellieu

For sponsor or guest inquiries, email: vivian@turpentine.co