You will use Claude Code in Assignment 1 (and potentially throughout the course). You will need access to LLM inference APIs in Assignments 2 and 3. You will need access to GPUs for Assignments 4 and 5. AWS provides additional computing resources, and every student registers an account in week one.
Start here. Harvard FAS provides a Claude Code license, please submit a request to get access.
Access the OpenAI, Anthropic, and Google models, provided by Harvard FAS ATG and routed through the MaDSys hybridInference proxy. We create an account for every enrolled student and post the credentials on Canvas, so there is nothing to register for. Please be frugal with your usage, as the cost can add up quickly.
Use an interactive Slurm job when a job is too long for your laptop, and use the course GPU partition for Assignments 4 and 5.
Registration is required of every student and the form closes after week one. Using the account is optional: run a small deployment on an EC2 instance if you want one, with no GPU needed. Protect the endpoint, set a billing alarm before launch, and stop the instance when you are finished.
| Work | Use | Why |
|---|---|---|
| Assignment 1 | Claude Code + AWS | Build the web UI with the course agent account, and deploy it on EC2 if you want it reachable. No GPU required. |
| Assignment 2 and Assignment 3 | Laptop/HPC + Harvard OpenAI/Gemini/Anthropic API | The model runs behind a commercial API. Any machine is enough; use AWS or HPC job when the experiment should run for hours. |
| Assignment 4 | HPC GPU (RTX PRO 6000 Blackwell) | You serve the model yourself. Use the course
gpu-cs2680 partition.
|
| Assignment 5 | HPC and/or API + AWS/CloudLab | You serve the agent using the provided GPU, you will optimize your model and serving engine, but you can also use a small number of API calls. |
| Final project | Laptop + model API, or HPC; CloudLab when necessary | Use the API for hosted models and the HPC when you need to serve or train a model. Use CloudLab only when the research question depends on bare-metal control or isolation. |
If a project needs hardware that none of these environments provides, ask the instructor while the scope can still change. Compute can sometimes be arranged; last-minute capacity cannot be promised.