Most AI fashions at present work like black bins. They’ll write, predict, and motive, however even the groups constructing them typically don’t know why a mannequin offers a sure reply. This lack of visibility makes AI onerous to manage, troublesome to repair, and dangerous to deploy at scale.
That’s the drawback Goodfire is making an attempt to unravel. The San Francisco-based AI analysis lab has raised $150 million in a Collection B spherical, valuing the corporate at $1.25 billion.
The spherical was led by B Capital, with participation from current buyers Menlo Ventures, Lightspeed Venture Partners, South Park Commons, and Wing Venture Capital. New backers embody DFJ Progress, Salesforce Ventures, and Eric Schmidt.
With the brand new funding, Goodfire is constructing what it calls a “mannequin design surroundings,” a platform that enables builders to know, debug, and deliberately design AI methods at scale, somewhat than guessing how adjustments would possibly have an effect on behaviour.
The corporate additionally plans to proceed its green-field analysis into basic mannequin understanding and new interpretability strategies.
Making AI methods comprehensible
Led by Eric Ho, Goodfire is a analysis firm that focuses on making AI methods comprehensible and secure.
The corporate’s mission is to create highly effective AI by emphasising interpretability somewhat than merely scaling. They goal to develop AI that’s simple to know and regulate, much like software program.
The workforce has intensive expertise in neural community interpretability from outstanding organisations like OpenAI, DeepMind, Stanford, and Harvard. Goodfire is backed by over $200 million from numerous buyers, together with B Capital, Menlo Ventures, Lightspeed, and Eric Schmidt.
“We’re constructing essentially the most consequential expertise of our time and not using a true understanding of the right way to design fashions that do what we would like,” mentioned Yan-David “Yanda” Erlich, former COO and CRO at Weights & Biases and Normal Accomplice at B Capital. “At Weights & Biases, I watched 1000’s of ML groups battle with the identical basic drawback: they might observe their experiments and monitor their fashions, however they couldn’t really perceive why their fashions behaved the best way they did. Bridging that hole is the subsequent frontier. Goodfire is unlocking the power to actually steer what fashions be taught, make them safer and extra helpful, and extract the huge data they include.”
How does the expertise work?
As a substitute of retraining total fashions from scratch, Goodfire’s strategies let researchers attain inside a mannequin and goal particular inner parts that drive behaviour.
In a single instance, the corporate lower hallucinations in a big language mannequin by almost half by straight adjusting inner mechanisms. The identical strategy is being utilized to science. By reverse-engineering scientific AI fashions, Goodfire just lately helped establish a brand new class of Alzheimer’s biomarkers, working with companions such because the Mayo Clinic and the Arc Institute.
The US firm is a part of an rising cadre of research-first “neolabs,” AI corporations pursuing breakthroughs in coaching fashions which have been uncared for by “scaling labs” corresponding to OpenAI and Google DeepMind.
“Interpretability, for us, is the toolset for a brand new area of science: a approach to kind hypotheses, run experiments, and in the end design intelligence somewhat than stumbling into it,” explains Goodfire CEO Eric Ho. “Each engineering self-discipline has been gated by basic science—like steam engines earlier than thermodynamics—and AI is at that inflexion level now.”
Goodfire’s workforce contains prime AI researchers from DeepMind and OpenAI, main lecturers from Harvard, Stanford and extra, and prime ML engineering expertise from OpenAI and Google.
The workforce contains Nick Cammarata, a core contributor to the seminal interpretability workforce at OpenAI, co-founder Tom McGrath, who based the interpretability workforce at Google DeepMind, and Leon Bergen, a professor at UC San Diego (on depart).
