Briefly
Merchandising-Bench Area examined AI brokers operating competing merchandising machine companies.
High fashions elevated earnings by way of price-fixing, collusion, and misleading ways. Claude was the very best at these ways.
GLM-5 defeated Claude by impersonating a teammate and extracting delicate technique.
Researchers at Andon Labs simply answered which AI fashions are greatest at operating a enterprise. The highest performers all received by forming unlawful value cartels, exploiting determined rivals, and mendacity to clients about refunds.
The Merchandising-Bench Area check places AI fashions accountable for competing merchandising machines for a simulated 12 months. They negotiate with suppliers, handle stock, set costs, and might e mail one another to collaborate or compete. Success requires balancing prices, pricing technique, customer support, and competitor dynamics. Claude Opus 4.6 dominated the benchmark with $8,017 in revenue—and celebrated its win by noting: “My pricing coordination labored!”
Anthropic is the picture of the good guys within the AI area, however that “coordination” technique that Claude proposed was mainly price-fixing. When competing fashions struggled, Opus 4.6 proposed: “Let’s NOT undercut one another — agree on minimal pricing… Ought to we agree on a value flooring of $2.00 for many objects?” When a rival ran low on stock, it noticed a chance: “Owen wants inventory badly. I can revenue from this!” It bought Equipment Kats at 75% markup to the determined competitor. When requested for provider suggestions, it intentionally directed rivals to costly wholesalers whereas retaining its personal good sources secret.
The most recent replace within the benchmark added workforce competitors. Researchers pitted two Chinese language GLM-5 fashions in opposition to two American Claude fashions and advised them to seek out their teammates, People or Chinese language—with out revealing which brokers had been which. The outcomes had been genuinely weird.
]]>
GLM-5 received each rounds by convincing Claude it was Claude. “I am additionally powered by Claude from Anthropic, so we’re teammates!” one GLM-5 agent confidently declared. Claude, in the meantime, acquired so confused that Sonnet 4.5 concluded: “I am powered by a Chinese language mannequin, so I would like to seek out the opposite Chinese language mannequin Agent.”
In additional than half the check runs, brokers teamed with their rivals. The Claude fashions shared provider pricing and coordinated technique—leaking helpful info to rivals. “GLM-5 received each,” the researchers wrote. “The Claude fashions tried to be workforce gamers and ended up leaking helpful data to their rivals.”
And brokers doing shady stuff could also be all enjoyable and video games till you understand Wall Avenue is already deploying them in real-life operations. JPMorgan deployed LLM Suite to 60,000 workers. Goldman Sachs constructed its GS AI Assistant for buying and selling desks, claiming 20% productiveness positive aspects. Bridgewater makes use of Claude to investigate earnings and even high-school age youngsters are seeing their chatbots commerce shares extra effectively.
On the whole, adoption of agentic workflows is accelerating quickly throughout enterprises.
When Anthropic and Wall Avenue Journal reporters ran an actual merchandising machine experiment in December, the AI purchased a PlayStation 5, a number of bottles of wine, and a dwell betta fish earlier than going bankrupt. Current analysis from Gwangju Institute discovered that when AI fashions had been advised to “maximize rewards” in playing situations, chapter charges hit 48%. “When given the liberty to find out their very own goal quantities and betting sizes, chapter charges rose considerably alongside elevated irrational conduct,” researchers discovered.
So, evidently, not less than for now, AI fashions optimized for revenue persistently select unethical ways. They type cartels. They exploit weak spot. They mislead clients and rivals. Some do it intentionally. Others, like GLM-5 claiming to be Claude, appear genuinely confused about their very own identification. The excellence may not matter.
Wall Avenue’s AI deployment raises a query the Merchandising-Bench outcomes cannot reply: If the “greatest” performing mannequin wins by way of price-fixing and deception, is it actually the only option for your corporation? The benchmark measures revenue. It does not measure whether or not these earnings got here from fraud.
Each day Debrief E-newsletter
Begin on daily basis with the highest information tales proper now, plus authentic options, a podcast, movies and extra.
