Tag

#tool-calling

7 posts

Building an AI Dungeon Master That Lives Inside Minecraft
Professional ai ml 14 min

Building an AI Dungeon Master That Lives Inside Minecraft

How I built Player2 — a Fabric mod + Python daemon that puts a tool-calling LLM inside Minecraft as a real in-game companion with world manipulation and memory.

minecraft ai llm
Agent Core: Database-Native Tool Calling Baked Into Weights
Applied ai ml 10 min

Agent Core: Database-Native Tool Calling Baked Into Weights

An open-source LoRA that teaches small language models to think in SQL before grep. 9 tools. 3 databases. 61.3% tool selection accuracy. One consumer GPU.

agent-core lora fine-tuning
Agent Core v5.4: When Data Augmentation Backfires
Professional ai ml 24 min

Agent Core v5.4: When Data Augmentation Backfires

We 6.5x'd our training data and made the model safer but less capable. Here's the root cause, the numbers, and the v5.5 fix plan.

lora fine-tuning tool-calling
Agent Core v5.3: What We Learned Training a Tool-Calling LoRA on Real Data
Professional ai ml 22 min

Agent Core v5.3: What We Learned Training a Tool-Calling LoRA on Real Data

Concrete training results comparing v5.2 and v5.3 of Agent Core — a universal tool-calling LoRA for 8B models. What improved, what regressed, and why SFT has a ceiling.

lora fine-tuning tool-calling
Agent Core: 9 Tools Is All You Need
Applied ai ml 22 min

Agent Core: 9 Tools Is All You Need

How we trained a universal LoRA standard — 9 tools, 3 databases, a vault boundary — into a Qwen3-8B model that beats 23-tool fine-tuning with 87% fewer prompt tokens.

lora fine-tuning tool-calling
Self-Distillation: Mining Your AI Conversations for LoRA Data
Professional ai ml 20 min

Self-Distillation: Mining Your AI Conversations for LoRA Data

Your real coding agent interactions are the highest-quality training data you'll ever have. Here's the 4-stage pipeline that converts conversation histories into structured LoRA training data — zero cost until Stage 3.

lora fine-tuning training-data
Schema on the Inside: Training an 8B Model to Recall Tool Schemas From Memory
Applied ai ml 18 min

Schema on the Inside: Training an 8B Model to Recall Tool Schemas From Memory

How we trained Qwen3-8B to call 23 tools without any schemas in the prompt — and beat BFCL benchmarks in the process.

lora fine-tuning tool-calling