The hidden sounds of rats: A new way to hear urban wildlife
Basis researchers hosted an exhibit at City Creatures in San Francisco where visitors could hear rats’ ultrasonic vocalizations through headphones fitted with 3D-printed rat ears.
News
The hidden sounds of rats: A new way to hear urban wildlife
Basis researchers hosted an exhibit at City Creatures in San Francisco where visitors could hear rats’ ultrasonic vocalizations through headphones fitted with 3D-printed rat ears.
Ship your interpreter
We had LLMs write precise mathematical rules, or a formal semantics, for how a small programming language should behave.
Reconstructing animal movements in 3D naturalistic environments from field measurements
We describe practical tools for reconstruction of animal tracks and their surroundings from videos collected outdoors.
Using LLM-based verification to eliminate bugs in Linux's network stack
We used LLMs to verify Linux's nftables `nft` CLI utility. Along the way, we found and patched bugs that had sat in the kernel for years.
Pact: trustworthy coordination for multi-agentic ecosystems
Multi-agentic ecosystems are becoming commonplace, but how can we trust them?
ExoPredicator: abstracting time and state for robot planning
We introduce ExoPredicator, a system that learns abstract world models for robot planning.
Building an unverified compiler with agents
Four agents spent 14 days and 93,000 lines of Lean building a verified JS-to-WASM compiler from scratch. The compiler ran; the proofs didn’t close.
AutumnBench: world model learning in humans and AI
We're releasing a new version of Autumn with human baseline results, AI performance comparisons, and an interactive benchmark for world model discovery.
Basis: designing a new kind of AI research organization
Written in 2022, this founding document defines Basis' vision and thesis of how to build a new kind of research organization.
Project MARA preview: modeling, abstraction, and reasoning agents
Project MARA aims to develop AI systems capable of performing everyday scientific discovery through active experimentation and abstract reasoning.
NeuroAI for AI safety
Basis contributed to a new technical roadmap, "NeuroAI for AI Safety," from Amaranth Foundation.
Linking cognitive strategy, neural mechanism, and movement statistics in group foraging behaviors
In a new paper, we combined cognitive neuroscience with statistical methods to model group foraging behavior.
MetaCOG: enhancing AI vision with human-inspired metacognition
In collaboration with Marlene Berke and the Computational Social Cognition Lab at Yale, we’re introducing MetaCOG, a probabilistic model that can learn a metacognitive model of a neural object detector and use it to improve the detector’s accuracy without feedback.
Linking algorithms to neural mechanisms in predictive memory models
In a new paper, we demonstrate biologically-plausible neural network models that can compute important features of predictive learning and memory systems.
Autumn: causal discovery through program synthesis
We're introducing AutumnSynth, an algorithm that synthesizes the source code of simple 2D video games from a small amount of observed video data.
No stories found.