Blog

Autonomous theory discovery

Automating AI model research with evolution

Bouncer 2.0: Leveraging Local Compute to Detect AI Slop

Use your unused Claude tokens for good

Every mngr plugin, explained

Fine-grained HTTP permissions for AI agents

How AI code review can make correct code worse

Blueprint: One-shot bigger coding tasks

Keystone-Eval: Our agentic benchmark for self-configuring agents

How to usefully run 1,000 agents in parallel

Bouncer: Heal your feed

How Offload Works: Inside the Rust CLI that sped up our tests by 6x

A case study in testing with 100+ of Claude agents in parallel

Usefully run hundreds of Claudes in parallel with mngr

Introducing Keystone: Building self-configuring agents

Offload: We made agents run our test suite 6x faster

Vet: Prevent coding agents from making mistakes

Latchkey: Use plain old REST instead of MCP

LLM-based Evolution as a Universal Optimizer

Beating ARC-AGI-2 with Code Evolution

A more radical Imbue

Choices and Knives

Digital Freedom Depends on Access Rights: Matt Boulos in Lawfare

How we made sandboxed coding agents 10x faster to start

A Healthy Ecosystem for AI Agents: Introducing the AFI

Sculptor: the missing UI for parallel coding agents

Empowering humans in the age of AI

Sculptor: Catch and fix issues as you code

Glenn McDonald: On Dungeons & Dragons, data alchemy, and radically open software

From bare metal to a 70B model: infrastructure set-up and scripts

Open-sourcing CARBS: how we used our hyperparameter optimizer to scale up to a 70B-parameter language model

Training a 70B model from scratch: open-source tools, evaluation datasets, and learnings

Sanitized open-source datasets for natural language and code understanding: how we evaluated our 70B model

'We need legal protections from AI’s risks': Matt Boulos in The Hill

Methodology for analyzing the individual comments to the NTIA’s AI RFC

The need for trust: Analyzing the individual comments to the NTIA’s AI RFC

Imbue Raises Fresh Capital, Amazon's Alexa Fund Joins Investor Lineup

Imbue raises $200M to build AI systems that can reason and code

Our technical hiring process

Bryden Fogelman: On coding agents and finding meaningful work at Imbue

In-person culture and habits

Where are the good policy ideas? Analyzing the NTIA's AI RFC

On the Stepwise Nature of Self-Supervised Learning

Scaling Laws For Every Hyperparameter Via Cost-Aware HPO

Our submission to the NTIA's AI accountability RFC

Towards guardrails, not guidelines: a policy framework for powerful AI systems

Update: The state of LLM ethical decision-making

The state of LLM ethical decision-making

Introducing Generally Intelligent

Our approach to safety

Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worlds (NeurIPS Spotlight Paper)

VICReg: Tutorial and lightweight PyTorch implementation

A PyTorch implementation of SIMONe

Jupyter Ascending: Sync notebooks to your editor

A PyTorch implementation of slot attention

A new AI research lab: Josh on the Machine Learning Engineered podcast

Understanding self-supervised and contrastive learning with "Bootstrap Your Own Latent" (BYOL)

Appendix for "Understanding self-supervised and contrastive learning with 'Bootstrap Your Own Latent' (BYOL)"