Goodfire raised $50 million in a Series A funding round to support its efforts to help enterprises understand and design artificial intelligence (AI) models.
The company will use the new funding to expand its research initiatives and further the development of its flagship interpretability platform, Ember, Goodfire said in an April 17 press release.
“Nobody understands the mechanisms by which AI models fail, so no one knows how to fix them,” Goodfire Co-founder and CEO Eric Ho said in the release. “Our vision is to build tools to make neural networks easy to understand, design and fix from the inside out.”
Goodfire’s research focuses on mechanistic interpretability, which aims to reverse engineer neural networks to gain insight into how they work, according to the release.
The company’s platform, Ember, decodes the neurons inside an AI model, gives direct access to its “internal thoughts,” and enables users to precisely shape the behaviors and improve the performance of their AI models, per the release.
Deedy Das, investor at Menlo Ventures, which led the funding round, said in the release that Goodfire is “cracking open that box” so enterprises can truly understand their AI systems.
AI startup Anthropic participated in the round, marking the company’s first investment in another startup, The Information reported April 17.
In the press release, Anthropic CEO and Co-founder Dario Amodei said Goodfire’s efforts will help companies better understand AI systems as the systems’ capabilities advance.
“Our investment in Goodfire reflects our belief that mechanistic interpretability is among the best bets to help us transform black-box neural networks into understandable, steerable systems — a critical foundation for the responsible development of powerful AI,” Amodei said.
When Anthropic said in March that it raised $3.5 billion in a Series E funding round to expand its AI offerings, it added that it would use the new funding in part to research mechanistic interpretability.
“With this investment, Anthropic will advance its development of next-generation AI systems, expand its compute capacity, deepen its research in mechanistic interpretability and alignment, and accelerate its international expansion,” the company said at the time in a press release.
Source: https://www.pymnts.com/
