‘프러버블리’, 환각 없는 고정밀 AI 구축 위해 900만 달러 유치

As LLMs have grown more powerful, hallucinations have proven stubbornly difficult to avoid. Errors pop up in even the smartest models, and while there are ways to catch those errors, the industry is still figuring out the best way to do it. Probably , which just raised $9 million in seed funding from Andreessen Horowitz, is trying to build a more rigorous way to catch those errors. As founder Peter Elias (pictured above) puts it, the company's goal is to prevent hallucinations and simple factual errors from ever reaching the user, and achieve the kind of 99.99% accuracy that’s common in deterministic systems but much more difficult to reach with AI. As it turns out, bringing LLMs to that level of accuracy requires rethinking many of the basic assumptions of AI engineering. Probably’s first product is a data science tool, built to produce quick answers from complex datasets. Each result comes with a citation and an audit trail for how it was developed, an increasingly common practice among AI tools. But keeping errors from creeping into those summaries required an elaborate harness system that Elias describes as a “data science mech suit.” The LLM’s first-pass answers are checked against a deterministic validator system, which bounces back any results that don’t match the dataset. Crucially, the LLM has been trained against the validator, and the whole system is optimized for fast and accurate answers, the company said. “What we learned building this was that the better your harness engineering is, the weaker the model can be,” Elias says. “If you can refine the context enough, the model does not have to work very hard to do the right thing. Basically, it's an exercise in reducing ambiguity.” That allows Probably’s data science tool to run on significantly smaller AI models. Elias says the current version is running on a model that’s “four classes weaker than the frontier models,” which means it can be run on local hardware (that is, a desktop computer instead of a data center), which reduces a huge amount of the token costs associated with AI use. It’s a welcome idea at a time when token costs are rising and many customers are reassessing their AI budgets . And, Elias’ idea doesn’t end with data science, as the same engine can be extended to cover use cases like accounting or medical services — as Elias puts it, “any precision-sensitive use case.” “I think it's really interesting that the big AI labs have not even attempted to do this,” Elias says. “They're incentivized not to, because they make money the more times you have to correct the model.” Topics AI , Andressen Horowitz , hallucinations , Probably When you purchase through links in our articles, we may earn a small commission . This doesn’t affect our editorial independence. Russell Brandom AI Editor Russell Brandom has been covering the tech industry since 2012, with a focus on platform policy and emerging technologies. He previously worked at The Verge and Rest of World, and has written for Wired, The Awl and MIT's Technology Review. He can be reached at russell.brandom@techcrunch.com or on Signal at 412-401-5489. View Bio June 18 Los Angeles Get an inside look at what it takes to scale and succeed from leaders at Mach Industries, Founders Fund, and Shinkei Systems. Through candid fireside chats and high-impact networking, you'll walk away with valuable insights and new connections. REGISTER NOW Most Popular The AI layoff wave is becoming a powder keg Connie Loizos Amazon CEO reportedly raised Anthropic model concerns before government crackdown Anthony Ha The FBI built its own replica small town to simulate real-world cyberattacks Zack Whittaker Meta's months-old AI unit is a soul-crushing gulag, say the engineers stuck inside it Connie Loizos Jeff Bezos's Prometheus raises $12B to build an ‘artificial general engineer' for the physical world Marina Temkin Cybersecurity researchers aren't happy about the guardrails on Anthropic's Fable Lorenzo Franceschi-Bicchierai Google just fired a warning shot in the AI subscription price wars Lucas Ropek Connie Loizos