Topics
Browse by topic
Each topic gathers the published signals, skills and background knowledge on one subject.
Topics with the most signals come first. Open one to see everything filed under it and its neighbours in the graph.
- 19
- topics
- 122
- published signals
- 22
- skills
- 27
- knowledge entries
Workflow
Operating patterns that make AI tools usable by real teams.
AI agents
Tools and patterns for multi-step AI systems that use tools.
Inference & deployment
Inference engines, deployment shapes and cost optimisation for large models.
Observability
Tracing, monitoring and post-incident review in production.
Frontier models
Generational updates of flagship models, their limits and price-performance.
On-device AI
Capable models running locally on laptops, phones or edge devices.
Agent runtimes & protocols
Runtimes, orchestration frameworks, sandboxes and protocols such as MCP: where agents run and how they reach tools.
Product strategy
Ways to decide what is worth learning, shipping and piloting first.
Coding agents
Agents that write, review and change code, and what they change in engineering practice.
Open-weight models
Releases of models with public weights, their licences and the open ecosystem.
Multimodal
Interfaces that combine text, images, speech or browser actions.
Safety & alignment
Safety incidents, red-teaming and alignment methods for models and agents, and controls on cyber capabilities.
Benchmarks & evaluation
How benchmarks are designed and how far to trust them, third-party evaluations and how they are scored.
Pricing & cost
Model pricing, compute and token costs, and what a task really costs.
Quantisation & speculative decoding
Quantisation, speculative decoding and other ways to make a model use less memory and generate faster.
AI for science
AI applied to mathematics, biomedicine and other research, and AI that speeds up research itself.
Training & post-training
Pre-training, reinforcement learning, fine-tuning and synthetic data, and the frameworks and environments for them.
Retrieval
Search, grounding and context-assembly workflows.
Knowledge graphs
Structured relations that connect concepts, entities and tasks.