Haize Labs

Haize Labs

Technology, Information and Internet

New York, NY 1,030 followers

it's a bad day to be a language model

About us

Haize Labs is the trust, safety, and reliability layer underpinning AI models in every industry and use case. By haizing (i.e. stress-testing and red-teaming) to discover and eliminate all failure modes, we enable the risk-free adoption of AI.

Website
https://haizelabs.com/
Industry
Technology, Information and Internet
Company size
2-10 employees
Headquarters
New York, NY
Type
Privately Held

Locations

Employees at Haize Labs

Updates

  • excited that our founders were featured on the Forbes 30 Under 30 list! 🕊️

    View profile for Leonard Tang, graphic

    co-founder & ceo @ haize labs | forbes 30u30

    excited to be featured on the Forbes 30 Under 30 AI list for Haize Labs alongside amazing companies like OpenAI, Anthropic, Cohere and more Haize Labs is building *the* end-to-end platform for building bullet-proof AI applications. if you want your AI applications to *finally* Get Safe, Get Reliable, and Get Production-Ready, you need to Get Haized. for early access to our platform, check out https://lnkd.in/gUXgpFx8 & https://lnkd.in/gnFTPGJd

    • No alternative text description for this image
    • No alternative text description for this image
    • No alternative text description for this image
  • Thanks for having us Matt Turck, Aman Kabeer, The MAD Podcast / Data Driven NYC! Long NYC AI 🕊️🗽

  • Haize Labs reposted this

    View organization page for Cerebras Systems, graphic

    42,524 followers

    Announcing Llamapalooza NYC on Oct 25! Join Cerebras for a one-of-a-kind event around fine-tuning and using llama models in production! Headliners include talks from Hugging Face, Cerebras, Crew AI. We'll also have food and drinks 🍹🍟 RSVP here: https://lu.ma/d3e81idy This event is brought to you by Cerebras, Hugging Face, Nasdaq, LaunchDarkly, Val Town, Haize Labs, CrewAI, Cloudflare, LiveKit.

    • No alternative text description for this image
    • No alternative text description for this image
    • No alternative text description for this image
    • No alternative text description for this image
  • Haize Labs reposted this

    View profile for Sahar Mor, graphic

    I help researchers and builders make sense of AI | ex-Stripe | aitidbits.ai | Angel Investor

    Two new jailbreaking techniques highlight how fragile state-of-the-art LLMs like GPT-4 are. The first from Haize Labs introduces a new attack method called Bijection Learning. The irony? The more advanced the underlying model is, the more successful the attack is. Bijection Learning uses custom-encoded languages to trick models into unsafe responses. Unlike previous jailbreak methods, it dynamically adjusts complexity to exploit small and large models alike without manual intervention. In their tests, even Claude 3.5 Sonnet, a model heavily fine-tuned for safety, was compromised with a staggering 86.3% attack success rate on a challenging dataset (HarmBench). It works by generating a random mapping between characters (a “bijection language”) and training the model to respond in this language. By adjusting the complexity of this mapping—such as changing how many characters map to themselves or using unfamiliar tokens—researchers can fine-tune the attack to bypass safety measures, making it effective even against advanced models. Full post https://lnkd.in/gtRysbTt The second method, by researchers at EPFL, addresses refusal training. The researchers discovered that simply rephrasing harmful requests in the past tense can often bypass safety mechanisms, resulting in an alarmingly high jailbreak success rate. For instance, rephrasing a harmful query in the past tense boosts the success rate to 88% on leading models, including GPT, Claude, and Llama 3. This mainly happens because supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) don’t always generalize well to subtle linguistic changes like tense modification. Neither of these techniques consistently equips the models to handle adversarial or unexpected reformulations, such as rephrasing harmful queries into the past tense. These studies highlight an alarming trend: as AI models become more capable, they also become more vulnerable to sophisticated jailbreaks. Attack #1: Bijection Learning https://lnkd.in/gtRysbTt Attack #2: Refusal training generalization to past tense https://lnkd.in/ggxnNGQ2 — Join thousands of world-class researchers and engineers from Google, Stanford, OpenAI, and Meta staying ahead on AI http://aitidbits.ai

    • No alternative text description for this image
  • couldn't be more ecstatic to have Constantin Weisser, PhD on the team!

    View profile for Constantin Weisser, PhD, graphic

    AI safety testing @ Haize | MIT PhD Physics, Stats | ex McKinsey AI

    Hi all, After over three exciting years at McKinsey, it's time for me to move on to a new chapter. I'm incredibly grateful for the opportunity to drive business impact by building AI solutions across six different industries. During this time, thanks to the support of many generous colleagues, I've grown from an academic into a professional who can solve business problems with technical solutions, productionalize them, and manage teams. A huge thank you to everyone who has been part of this journey! I am excited to come to New York City to join Haize Labs as a Member of Technical Staff and employee #1. Haize aims to revolutionize safety testing of large language models through automated redteaming, precise evaluations, and guardrails for safer usage (https://shorturl.at/Mfr5j). I can't wait to see where this story takes us. If you are passionate about working towards safer AI systems, please reach out!

    • No alternative text description for this image
  • Haize Labs reposted this

    View profile for Leonard Tang, graphic

    co-founder & ceo @ haize labs | forbes 30u30

    Excited to share a deep dive of the red-teaming research we've been doing for OpenAI at Haize Labs 🕊 In month before release before the new o1 series, we've been rigorously haizing (stress-testing) the safety and adversarial robustness of their models. Many thanks to Nathan Labenz for having us on the Cognitive Revolution podcast to chat about this work! Listen here for the details about our research and engineering intuitions for automated red-teaming of frontier AI systems. Shoutout especially to Brian Huang and Aidan Ewart for their amazing automated red-teaming efforts 🕊

    Red Teaming o1 Part 1/2–Automated Jailbreaking w/ Haize Labs' Leonard Tang, Aidan Ewart& Brian Huang

    Red Teaming o1 Part 1/2–Automated Jailbreaking w/ Haize Labs' Leonard Tang, Aidan Ewart& Brian Huang

    cognitiverevolution.ai

  • Haize Labs reposted this

    View profile for Akhil Paul, graphic

    Startup Helper | Advisor | Caparo Group

    🚀𝘽𝙍𝙀𝘼𝙆𝙄𝙉𝙂: Business Insider just dropped a list of 85 of the most promising startups to watch for 2024… 📈Some of the largest outcomes (Amazon, Airbnb, Stripe, Uber etc) we’ve seen in 𝗩𝗲𝗻𝘁𝘂𝗿𝗲 𝗖𝗮𝗽𝗶𝘁𝗮𝗹 have come on the back of hard times. 💪 Only the strongest & most resilient teams survive. 🔍 Business insider asked top venture capitalists at firms including Accel, GV, Founders Fund, Greylock, Khosla Ventures & IVP to name the startups they’re most excited by. 🎯 Flagging 4 companies from the list I work with that are worth having on the radar👇 —— 1️⃣ Gamma - An AI-powered content creation tool for enterprise customers. The tool enables users to create presentations, websites, and documents quickly. 👥 Founders: Grant Lee, Jon Noronha, James Fox 💰 Funding: $21.5Mn 🚀 Investors: Accel, LocalGlobe, Script Capital 🌟 Why it’s on the list? Gamma has already amassed 20Mn+ users with 60M+ gammas created, and is profitable. It is reinventing creation of websites, presentations & documents. —— 2️⃣ Sema4.ai - It is building enterprise AI agents that can reason, collaborate, and act. 👥 Founders: Antti Karjalainen, Paul Codding, Sudhir Menon, Ram Venkatesh 💰 Funding: $54Mn 🚀 Investors: Benchmark, Mayfield Fund, Canvas Ventures 🌟 Why it’s on the list? The company is developing AI agents that can move beyond simple repetitive tasks and actually solve real-world problems, taking into account the unique context of the organization and working seamlessly with existing teams. —— 3️⃣ Mutiny - An account-based AI platform that helps companies unify sales and marketing to generate pipeline and revenue from their target accounts at scale. 👥 Founders: Jaleh Rezaei, Nikhil Mathew 💰 Funding: $72Mn 🚀 Investors: Sequoia, Tiger, Insight, Cowboy Ventures 🌟 Why it’s on the list? Mutiny leverages AI to help B2B companies generate pipeline & revenue from their target accounts through AI-powered personalized experiences, 1:1 microsites & account intelligence - more important than ever in the current software consolidation cycle / market & budget environment. —— 4️⃣ Haize Labs - Automatic stress testing of large language models. 👥 Founders: Leonard Tang, Steve Li 🌟 Why it’s on the list? Haize promises to "robustify" any large language model through automated red-teaming that continuously stress tests and identifies vulnerabilities. As models evolve, the question of how to make sure they're secure becomes increasingly difficult to answer. —— 🌐 The biggest themes on the list this year? 📊 Data infrastructure 🔒 Security 🤖 Personalised agents —— 🔎It’s helpful for 𝐀𝐧𝐠𝐞𝐥𝐬 to keep on top of lists like these to track & source new opportunities. 🔗 to the FULL list in comments. 🚀 Any companies not on the list that should be? Tag them in comments. 📣 PS- If you enjoyed this & found it valuable, 👉🏽follow me Akhil Paul for more! #startups #venturecapital #investing #technology #angelinvesting

    • No alternative text description for this image
  • Haize Labs reposted this

    View profile for Akash Bajwa, graphic

    Principal at Earlybird Venture Capital

    A consistent theme in discussions I've had with AI Application founders is a request for red teaming solutions. Combined with regulatory frameworks like the EU AI Act adding further pressure, there's more attention going towards both human and model-based ways of scaling red teaming of LLMs where the immense combinatorial space is difficult to address. Protect AI acquired SydeLabs to expand their AI security suite last week, but there are others like Haize Labs, Promptfoo and more devising innovative new ways of scaling automated red teaming without the associated trade off in model performance. https://lnkd.in/en5_9jMP

    Red Teaming As A Service

    Red Teaming As A Service

    akashbajwa.substack.com

Similar pages

Browse jobs