Observed Signal · Oct 10, 2026 · Funding · Source: Trending Topics (DACH/CEE Innovation & Tech) · Impact: 4/5 · Sentiment: Positive
Sabi Raises $50M Seed for Brain-Reading AI Cap
Sabi, a Silicon Valley startup, has raised a $50 million seed round led by Khosla Ventures to develop a baseball cap that reads brain signals via EEG to convert thoughts into text and AI commands. The cap uses non-contact dry EEG sensors that measure brain activity through hair, eliminating the need for gel or surgery. The company has designed a custom EEG chip and is training a Brain Foundation Model on over 100,000 hours of EEG data. The product aims to enable faster human-AI interaction, with a prototype planned for CES in January. However, a Meta study shows high error rates in EEG-based brain-to-text decoding (67% character error), highlighting technical challenges. Sabi has not yet released independent accuracy data.
This is a notable seed funding round for a novel brain-computer interface technology aimed at enabling thought-to-text and thought-to-AI commands, which could have transformative implications for human-computer interaction and AI accessibility. While the technology is early-stage, the involvement of major investors and the large dataset signals significant potential impact on the AdTech ecosystem by enabling new forms of engagement and personalized experiences.
Track Khosla Ventures Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- Sabi raised $50 million in a seed round led by Khosla Ventures, with participation from Accel, Initialized Capital, DST Global, Collaborative Fund, Ascend, and Kevin Weil.
- Sabi is building a baseball cap that uses dry, non-contact EEG sensors to capture brain signals through hair and convert thoughts into text or AI commands.
- Sabi has designed its own EEG chip and is training a Brain Foundation Model on over 100,000 hours of EEG recordings.
- A first prototype is planned for demonstration at CES in Las Vegas in January.
- A Meta study with 35 participants showed a 67% average character error rate for EEG-based brain-to-text decoding, highlighting the technical challenge.
Connected Companies & Entities
10 Entities mapped“Sabi has just raised a $50 million seed round led by Khosla Ventures...”
“participation from Accel, Initialized Capital, DST Global, Collaborative Fund, Ascend and Kevin Weil...”
“participation from Accel, Initialized Capital, DST Global, Collaborative Fund, Ascend and Kevin Weil...”
“participation from Accel, Initialized Capital, DST Global, Collaborative Fund, Ascend and Kevin Weil...”
“Kevin Weil, OpenAI’s former chief product officer...”
“The team includes alumni of Kernel, Apple, Microsoft, Meta and Nike....”
“Kameraspezialist Nikon hat das Siegervideo seines renommierten Mikroskopie-Wettbewerbs Small World in Motion nachträglich disqualifiziert...”
“The team includes alumni of Kernel, Apple, Microsoft, Meta and Nike....”
“The team includes alumni of Kernel, Apple, Microsoft, Meta and Nike....”
“The team includes alumni of Kernel, Apple, Microsoft, Meta and Nike....”
Ontology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Cerebionics Develops Non-Invasive BCI to Translate Intent into Machine Commands
Cerebionics, a Norwegian startup founded by Agnessa Pedersen, is developing a non-invasive brain-computer interface (BCI) platform that uses EEG electrodes to translate human intent into commands for machines. The platform aims to provide an additional control channel for various systems, including drones, unmanned ground vehicles, and C2 APIs. Unlike Neuralink's invasive approach, Cerebionics focuses on higher-level commands rather than fine motor control. The startup has tested its technology with Ukrainian soldiers, receiving feedback to improve robustness. Cerebionics has received commercial interest through letters of intent and is currently scaling its team. The company anticipates applications in defense, healthcare, consumer, and industry, with future potential in gaming and integration into wearables like smart glasses.
Goodfire raises $150M to decode AI 'alien brains'
Goodfire, an AI research startup focused on mechanistic interpretability, has raised a $150 million Series B at a $1.25 billion valuation. Co-founded by Dan Balsam (co-founder & CTO), Eric Ho, and Tom McGrath, the company builds tools to inspect and intervene at neuron-level representations inside large models. Goodfire says its work has produced practical outcomes: identifying potential epigenetic biomarkers for earlier Alzheimer’s detection with partner Primmamenta, deploying inference-time interpretability guardrails with partners like Rakuten, and detecting neuronal "hallucination signatures" that can be used as training signals to reduce hallucinations. The interview discloses the host Joe Lazer is a small seed investor in Goodfire and places the company’s approach as a safety- and reliability-focused complement to mainstream LLM scaling efforts.
Encord trials brain-wave data to train physical AI
Encord is running trials in a San Leandro warehouse to create new training data for robotics by combining egocentric video, arm muscle sensors, leader-follower rigs and brain-wave measurements. The brain-wave headset used in the trial was built by German startup Zander Labs; Encord plans to tag datasets with mental-state signals (error, intent, surprise) to test whether they improve robot model performance. Encord says physical training data is scarce and expensive to produce, driving a business model around manufacturing datasets for manipulation tasks. Company leaders estimate the scale needed to advance physical AI is orders of magnitude larger than current corpora, and Encord is experimenting with dense annotation and multimodal signals to increase dataset value.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.