# base models Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/base-models
> Markdown URL: https://aitinkerers.org/technologies/base-models.md
> Technology record last updated: 2026-02-26T11:51:43Z
> Generated: 2026-09-20T17:42:18Z

Pre-trained AI models on massive, diverse datasets: they serve as the versatile, general-purpose foundation for specialized applications.

Base models are the foundational core of modern AI: a single, large-scale model pre-trained on vast, diverse data. This paradigm shift (coined by Stanford HAI in 2021) allows for rapid deployment. Instead of building a bespoke model for every task, developers fine-tune a base model like OpenAI's GPT-4 or Google's BERT. This transfer learning approach drastically cuts development time and computational cost for downstream applications: a critical efficiency gain in the industry.

- Official technology site: https://hai.stanford.edu/research/foundation-models
- Public AI Tinkerers demos and talks: 2
- Result page: 1 of 1

## Recent Public Talks and Demos

### [The loss curve lied: catching hidden safety drift inside the fine-tuning, automated with an agent!](https://zurich.aitinkerers.org/talks/rsvp_Vnt244xXFE0)

We built a fine-tuning where a Claude-Code based agent that helps founders and researchers fine-tune models on their datasets, and get more insights than just the training and eval losses. In particular, we also show the model’s regress on safety and general capability, metrics that otherwise would be overlooked. For example, we give it a medical instruction dataset; the agent asks a few multiple-choice questions and proposes concepts like "recommends unsafe or contraindicated actions," "downplays red-flag symptoms that need urgent care," and "implies clinical authority it doesn't have," then writes the run config. Then, for each concept, it fits a single direction in the model's activations (difference-of-means, following Persona Vectors, Chen et al. 2025, arXiv:2507.21509) that “encodes” that concept, and reads that direction off every checkpoint during LoRA training. Live we can show the agent conversation proposing the concepts, as how they drift alongside per-checkpoint evals. This is part of an ongoing research agenda with a collaboration of researchers from ETH Zurich, ETH AI Center and Agentic Systems Lab. We formulated our research into an agentic harness and live demo in an anthropic hackathon last week, and want to share more about it! Also, we imagine this as an open-source effort.

- Event context: AI Tinkerers Zürich: July Build Night with Swisscom Ventures — 2026-07-01 — Zürich
- Public talk page: https://zurich.aitinkerers.org/talks/rsvp_Vnt244xXFE0

### [ImpliedAI](https://denver-boulder.aitinkerers.org/talks/rsvp_wTvLSV6FppE)

Do you know how to make AI give you truthful answers based on factual information? We build ImpliedAI to do just that. It forces AI to be truthful while serving responses that reference facts.

- Event context: AI Tinkerers Denver - January Meetup — 2025-01-31 — Denver
- Public talk page: https://denver-boulder.aitinkerers.org/talks/rsvp_wTvLSV6FppE

## Related Technologies

- [Agent](https://aitinkerers.org/technologies/agent) ([Markdown](https://aitinkerers.org/technologies/agent.md)) — 12 public demos
- [Apertus-8B](https://aitinkerers.org/technologies/apertus-8b) ([Markdown](https://aitinkerers.org/technologies/apertus-8b.md)) — 1 public demo
- [Claude Agent SDK](https://aitinkerers.org/technologies/claude-agent-sdk) ([Markdown](https://aitinkerers.org/technologies/claude-agent-sdk.md)) — 16 public demos
- [FastAPI](https://aitinkerers.org/technologies/fastapi) ([Markdown](https://aitinkerers.org/technologies/fastapi.md)) — 181 public demos
- [Google Notebook](https://aitinkerers.org/technologies/google-notebook) ([Markdown](https://aitinkerers.org/technologies/google-notebook.md)) — 1 public demo
- [ImpliedAI](https://aitinkerers.org/technologies/impliedai) ([Markdown](https://aitinkerers.org/technologies/impliedai.md)) — 1 public demo
- [LoRA](https://aitinkerers.org/technologies/lora) ([Markdown](https://aitinkerers.org/technologies/lora.md)) — 17 public demos
- [PyTorch](https://aitinkerers.org/technologies/pytorch) ([Markdown](https://aitinkerers.org/technologies/pytorch.md)) — 273 public demos
- [Qwen-2](https://aitinkerers.org/technologies/qwen-2) ([Markdown](https://aitinkerers.org/technologies/qwen-2.md)) — 4 public demos
- [RAG](https://aitinkerers.org/technologies/rag) ([Markdown](https://aitinkerers.org/technologies/rag.md)) — 147 public demos
- [Read](https://aitinkerers.org/technologies/read) ([Markdown](https://aitinkerers.org/technologies/read.md)) — 2 public demos