Sourced knowledge on LLMs
Structured, sourced knowledge on how LLM systems actually behave in production.
Why this site exists
This site exists because most LLM resources blur the line between hype and evidence. Claims go unsourced, untested, and overconfident. Here, every article starts from a precise question, cites its sources, and separates what is established from what is speculative. For practitioners building real systems, and decision-makers who need grounded judgment without the buzzwords.
Where to start
Three articles to get started
Recent articles
What the labs publish about their models — and what they leave out
A same-day survey of the model pages at Anthropic, OpenAI and Google: four facts decide an architecture, and none of the three publishes all four.
Agentic red teaming — when the LLM is no longer the main target
Why auditing an agentic system means widening the perimeter beyond the LLM: the Dreadnode taxonomy of 5 fronts, the OWASP ASI framework, an audit methodology and actionable mitigations.
The web getting ready for AI agents — where the transition is actually happening
An empirical 2026 survey of the web facing AI agents: outbound-click disintermediation, headless bimodality between enterprise and consumer, agents ready only for bounded use cases, and fragmented bidirectional standards (MCP, NLWeb, Cloudflare Pay Per Crawl, llms.txt).
Amazon Nova — AWS's model strategy facing OpenAI and Google
Launched in December 2024, the Nova family is Amazon's first genuinely competitive line of proprietary AI models. Aggressive pricing, native Bedrock integration, Nova 2 with extended reasoning: a balanced overview of an actor playing its own card in a landscape dominated by OpenAI, Anthropic and Google.
Cohere — enterprise-first AI from Toronto
Co-founded by a co-author of the Transformer paper, Cohere builds LLMs exclusively for enterprises: private deployments, native RAG, extended multilingualism. A portrait of a B2B player that refuses to compete with its own customers.
Explore by territory
The science behind the models
- Architecture & functioning
- Training
- Tokens & context
- Evaluation
Companies, labs, and models
- Companies
- Models
- Ecosystem
Hardware, cloud, energy
- GPUs & chips
- Memory & storage
- Datacenters & energy
- Supply chain
For working with LLMs
- Orchestration & agents
- Development
- Protocols
Getting the most out of LLMs
- Optimization
- Alignment
- Specialization
Beyond the technical
- Safety
- Governance
- Environment
What this site is for
Labo LLM publishes open-access technical knowledge on LLMs, grounded in public research and reproducible experimentation. Content is produced by a personal applied-research lab that documents its pipeline: public method, cited sources, systematic dating.