fine-tuning
11 free lessons tagged fine-tuning across AI, Business. Each one is a short sequence of focused steps with narration and a five-question quiz at the end — take them in any order, no signup required.
Model Collapse, and the Rule That Avoids It
Training on your own model's output degrades it, and the widely cited result rests on an assumption people rarely notice: that synthetic data replaces real data. Follow-up work showed accumulating synthetic alongside real bounds the error instead. This lesson covers both stages of collapse, why the rule is accumulate rather than replace, how to set a mixing ratio, and the evaluation discipline.
Generation: Getting Coverage, Not Just Volume
Prompt a model for a thousand examples and you get one example a thousand times, with the nouns changed. This lesson covers why raising temperature does not fix that, the seed-conditioning trick that does, how Self-Instruct and Evol-Instruct systematise it, programmatic generation where ground truth is known by construction, and how to measure whether a dataset actually covers its input space.
When Generating Data Beats Collecting It
Synthetic data is roughly three orders of magnitude cheaper than human annotation, and cheapness is the least interesting thing about it. This lesson establishes what generation can and cannot manufacture: it produces coverage and format, never information the generator lacks, and the one exception is verifiable domains, where a checker turns generation into search.
Training Diffusion Language Models at Scale
What it takes to train a diffusion language model to billions of parameters: the from-scratch recipe, adaptation from an autoregressive checkpoint, the supervision economics, and the capability that bidirectional training gets for free.
The Options Nobody Compares, and Changing Your Mind
The fine-tuning versus retrieval framing hides several options that are often better than either. This lesson covers long context and why it does not replace retrieval, prompt caching as a cost lever, agentic retrieval, continued pretraining, and how to revisit a decision that was right when you made it.
Building Both: LoRA, Data, and the Retrieval Pipeline
The decision is only half the work. This lesson covers what building each actually involves: parameter-efficient fine-tuning with LoRA and why it made the technique accessible, the training data problem that stalls most projects, the retrieval pipeline end to end, and how to combine them into one system.
What Each Technique Actually Changes
Fine-tuning and retrieval are usually presented as alternatives when they change different things. This lesson separates them precisely: fine-tuning adjusts weights and teaches behaviour, retrieval supplies context and teaches nothing, and the question that decides between them is whether your problem is knowledge or form.
Direct Preference Optimization: DPO, IPO, KTO, and SimPO
A deep dive into DPO (Rafailov et al. 2023) and its successors — how they reformulate RLHF as a classification problem, the math behind the implicit reward, and where each variant wins or loses against PPO-based pipelines.
LLM Post-Training: SFT, RLHF, DPO, and Modern Alignment Recipes
A deep dive into how raw pretrained language models become helpful assistants — from supervised fine-tuning on curated demonstrations, through reward modeling and PPO-based RLHF, to modern direct alignment methods like DPO and the recipes used in Llama 3, Llama 4, and DeepSeek.
The Data Foundation for Enterprise AI
The model is rarely the bottleneck. This lesson examines why data readiness — quality, governance, lineage, and access — is the primary constraint on enterprise AI value, with a practical scorecard, and a clear-eyed comparison of RAG versus fine-tuning economics.
Open Weights vs Closed APIs: The Real Tradeoffs
An honest look at the open-weights vs closed-API choice for LLMs in 2026 — covering data privacy, cost at scale, fine-tuning, latency, regulatory concerns, and the gap in raw capability per dollar.