<p><span class="legendSpanClass"><strong>SAN FRANCISCO</strong> &#8212;</span> <u><a href="https://edge.prnewswire.com/c/link/?t=0&;l=en&;o=4612412-1&;h=2379072455&;u=https%3A%2F%2Fwww.goodfire.ai%2F&;a=Goodfire" target="_blank" rel="nofollow noopener">Goodfire</a></u>—the AI research lab using interpretability to understand, learn from, and design models—announced a $150 million Series B funding round at a $1.25 billion valuation. The round was led by B Capital, with participation from existing investors Juniper Ventures, Menlo Ventures, Lightspeed Venture Partners, South Park Commons, and Wing Venture Capital, and new investors DFJ Growth, Salesforce Ventures, Eric Schmidt, and others. This funding, coming less than a year after its Series A, will enable Goodfire to advance frontier research initiatives, build the next generation of its core product, and scale partnerships across AI agents and life sciences.</p>
<p>Interpretability is the science of how neural networks work internally, and how modifying their inner mechanisms can shape their behavior—e.g., adjusting a reasoning model&#8217;s internal concepts to change how it thinks and responds. Interpretability also enables AI-to-human knowledge transfer, i.e., extracting novel insights from powerful AI models. Goodfire recently identified a novel class of Alzheimer&#8217;s biomarkers in this way, by applying interpretability techniques to an epigenetic model built by Prima Mente—the first major finding in the natural sciences obtained from reverse-engineering a foundation model.</p>
<p>&#8220;We are building the most consequential technology of our time without a true understanding of how to design models that do what we want,&#8221; said Yan-David &#8220;Yanda&#8221; Erlich, former COO and CRO at Weights &; Biases and General Partner at B Capital. &#8220;At Weights &; Biases, I watched thousands of ML teams struggle with the same fundamental problem: they could track their experiments and monitor their models, but they couldn&#8217;t truly understand <i>why</i> their models behaved the way they did. Bridging that gap is the next frontier. Goodfire is unlocking the ability to truly steer what models learn, make them safer and more useful, and extract the vast knowledge they contain.&#8221;</p>
<p>Most companies building AI models today build their models as black boxes. Goodfire believes that that approach means that society is currently flying blind—and that deeply understanding how models work &#8220;under the hood&#8221; is critical to building and deploying safe, powerful AI systems. The company is pursuing research which turns AI into something that can be understood, debugged, and intentionally designed like written software.</p>
<p>&#8220;Interpretability, for us, is the toolset for a new domain of science: a way to form hypotheses, run experiments, and ultimately <i>design</i> intelligence rather than stumbling into it,&#8221; explained Goodfire CEO Eric Ho. &#8220;Every engineering discipline has been gated by fundamental science—like steam engines before thermodynamics—and AI is at that inflection point now.&#8221;</p>
<p>Goodfire is part of an emerging cadre of research-first &#8220;neolabs&#8221;—AI companies which are pursuing new breakthroughs in training models which have been neglected by &#8220;scaling labs&#8221; such as OpenAI and Google DeepMind.</p>
<p>So far, the company has shown the value of their interpretability-driven approach across two key domains: scientific discovery and model design.</p>
<p>On the scientific discovery front, Goodfire has focused on deciphering scientific foundation models with partners like Mayo Clinic, Arc Institute, and Prima Mente, exemplified by their identification of a new class of biomarkers for Alzheimer&#8217;s detection. Because AI models already surpass human understanding in many scientific domains, like materials discovery and protein folding, studying how those models work can extract novel insights and expand the horizons of human knowledge. The company plans to continue scaling its pipeline for scientific discovery with new collaborators.</p>
<p>On the model design front, Goodfire has focused on teaching models directly through their internal mechanisms. The company has recently developed methods to efficiently retrain a model&#8217;s behavior by precisely targeting parts of its inner workings. One application of these methods reduced hallucinations by half in a large language model. Goodfire is betting that this approach will underpin a paradigm shift in how AI is built, where AI can be made far more reliable and people can precisely and efficiently dictate how models should behave without off-target effects.</p>
<p>The new funding will support Goodfire&#8217;s work to rethink training and build a &#8220;model design environment&#8221;—a platform for understanding, debugging, and intentionally designing AI models at scale. The platform will leverage frontier interpretability techniques to allow users to reach inside models, identify the parts responsible for behaviors they want to change, and specifically train or intervene on those subunits.</p>
<p>The company also plans to continue its green-field research into fundamental model understanding and new interpretability methods.</p>
<p>Goodfire&#8217;s team comprises top AI researchers from DeepMind and OpenAI, leading academics from Harvard, Stanford and more, and top ML engineering talent from OpenAI and Google.</p>

PALO ALTO – Quantum Computing company D-Wave Quantum Inc. announced that it has selected Boca…
EA SPORTS has revealed its official Super Bowl LX Simulation with Madden NFL 26, predicting…
Mercedes-Benz is marking 140 years of automotive innovation with a new S-Class lineup of vehicles…
SAN FRANCISCO -- Kindred, the global home swapping platform, has raised $125 million over two rounds…
SAN FRANCISCO -- RapidFort, a company specializing in software supply chain security, today announced $42…
Meta Platforms, Inc. (META) released its Fourth Quarter 2025 Results and CEO Mark Zuckerberg and…