Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
LLMs and hundreds of tools
This talk explores the capability of large language models to effectively utilize hundreds of tools, examining practical applications and limitations.
Can LLMs use 100s of tools?
Builds reliable, auditable AI agents using planning and regulated MCP tool integration.
Related projects
How to evaluate LLMs?
Amsterdam
This talk demonstrates practical methods to evaluate LLM outputs using judges, cosine similarity, and JSON schema validators to…
AI on Trial: Fine-Tuning LLMs to Judge other LLMs; data, results and challenges
London
We will present data, experiments, results, and challenges of training language models to evaluate other models, plus insights…
LLM-assisted/automated Data Analysis
Dublin
The talk demonstrates a proof‑of‑concept where an LLM reads a dataset, infers structure, writes analysis code, runs queries,…
Lessons from building an LLM-first framework
London
Explore how Tonk enables non‑coders to quickly update multiplayer applets by limiting context to the frontend and using…
Keeping an "AI" on LLMs with Langfuse
London
Learn how to self‑host Langfuse for LLM observability, covering setup, tracking user queries, inputs, retrieved data, and practical…
adapting LLMs to directly generate diffs of text
London
Learn how to adapt large language models to directly produce text diffs, covering the workflow, challenges encountered, and…