# Articles tagged with: project

> Anthus builds self-aligning AI systems: custom models, agent harnesses, evaluation loops, and unattended automation with a human in the loop, grounded in production operations since 2007.

- [Distilling an Aligned Jev System into a Classifier You Own](https://anth.us/articles/distilling-jev-into-a-classifier/index.md): A Jev decision model aligned with 140 human labels taught a 66M-parameter DistilBERT that scored 0.912 against the human label, two points above its teacher, at 5.6 to 15 ms an item. The accuracy is the least general part; the per-slice ship gate is the part to copy. (2026-09-21)
- [An agent skill for not sounding like an agent](https://anth.us/articles/an-agent-skill-for-not-sounding-like-an-agent/index.md): "Sound less like AI" isn't a prompt problem. It's a tooling problem: give your copy-editing agent a deterministic slop detector, checked against your publication's own rules instead of a generic notion of "human." Humanus is what that looks like as a real, open-source tool. (2026-09-08)
- [Inspected by Pudicus](https://anth.us/articles/inspected-by-pudicus/index.md): Pudicus makes git hooks actually run, so agent swarms scan for secrets before they commit. Once a secret is in history, it's expensive to unwind. (2026-08-31)
- [The Turn Detection Trap: When 100% Accuracy is Wrong](https://anth.us/articles/domain-specific-turn-detection/index.md): We fine-tuned MobileBERT for turn detection and achieved 100% accuracy. Then we realized we hadn't solved turn detection at all—we had just built a very expensive punctuation detector. (2025-11-22)
- [How to Make a Text Classifier Using an LLM](https://anth.us/articles/fine-tuned-classification-with-confidence/index.md): Classification-with-Confidence follows an LLM classifier from Yes-or-No token probabilities through calibration, routing, and task-specific fine-tuning. (2025-09-17)
- [Give an Agent a Tool](https://anth.us/articles/give-an-agent-a-tool/index.md): A demonstration of a fundamental paradigm shift in computer programming: from writing explicit code for every scenario to giving intelligent agents the right tools and letting them figure it out. This project shows how the same task that requires hundreds of lines of complex branching logic in trad… (2025-09-15)
- [LangChain by Example](https://anth.us/articles/langchain-by-example/index.md): Learn how easy it can be to implement LLM applications through real-world AI use cases, like: What can I make with this one avocado? (2024-08-25)