Red Teaming
Red Teaming on Beyond Market Intelligence: a running collection of 4 stories we have gathered and hand-picked because they are worth your time. Every post here touches on red teaming in some way — the news, the analysis, the deep dives, and the occasional surprise find. Acme AI is the next-generation, AI-powered spreadsheet platform built to replace Excel and redefine how analysts, data scientists, and enterprise teams work with data. New stories are added to this page as we find them, so check back if you want to keep up with what is happening around red teaming, or subscribe to the RSS feed to get them as soon as they are published. Browse the collection below, or head back to the homepage to see everything Beyond Market Intelligence is covering right now.
Abliteration.ai is making a business out of removing AI guardrails
Abliteration.ai is reshaping the AI landscape by providing access to powerful AI models without traditional guardrails. Their premise is straightforward: equipping defenders with the same tools as potential adversaries ultimately strengthens cybersecurity. This approach challenges conventional wisdom, offering a proactive strategy for identifying and mitigating vulnerabilities. The move reflects a broader shift in how we approach AI security, as evidenced by the evolving demands on energy infrastructure—utilities are actively seeking partnerships with fusion startups to meet the strain of AI data centers. Explore Abliteration.
Multi-turn attacks broke AI models 88% of the time — single-turn testing missed it, Cisco AI security lead warns at VB Transform 2026
Recent research reveals a concerning vulnerability in AI models: multi-turn attacks exploit conversational adaptability, succeeding 88.3% of the time – a rate single-turn testing completely misses. Cisco’s AI security lead, Amy Chang, highlighted this critical finding at VB Transform 2026, emphasizing the need to move beyond snapshot evaluations. With over half of enterprises experiencing agent security incidents, robust, continuous testing mimicking real-world adversarial interactions is paramount. As Box's CISO Heather Ceylan stated, "You have to pressure test your agents."
Evals are the new PRD, Expedia’s AI chief tells VB Transform 2026
Expedia’s chief AI and data officer, Xavi Amatriain, is redefining product development, asserting that "evals are the new PRD." This shift prioritizes embedding security and design principles directly within evaluation processes, even before coding begins, leveraging AI-assisted code generation. Amatriain advocates for risk-calibrated governance layers, minimizing restrictive guardrails to maintain feedback loops and user agency, particularly emphasizing that users should retain the final click for transactions.
Google's Gemini 3.6 Flash model cuts AI agent token costs by up to 65% on long horizon engineering tasks —and 3.5 Pro is on the way
Google DeepMind has unveiled the Gemini 3.6 Flash model, engineered to significantly reduce AI agent token costs—cutting them by up to 65% on demanding long-horizon engineering tasks. Priced competitively at $1.50/$7.50 per million input/output tokens, it joins the Gemini 3.5 Flash-Lite ($0.30/$2.50) and specialized Gemini 3.5 Flash Cyber models, all designed to enhance speed, intelligence, and scalability. These advancements prioritize efficiency, streamlining workflows and empowering developers—a strategy mirrored in Weka's recent storage platform innovations. Gemini 3.5 Pro remains