Computing Resources You will Use

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 and CloudLab provide additional computing resources as needed.

Request the necessary resources in week one: Claude Code, model API, HPC GPU, and AWS accounts.

Required · Assignment 1

Claude Code

Start here. Harvard FAS provides Claude Code license, please submit a request to get access.

Required · Assignments 2 and 3

Model API access

Access the OpenAI, Anthropic, and Google models, funded by Harvard FAS ATG and routed through the MaDSys hybridInference proxy. Please be frugal with your usage, as the cost can add up quickly.

Required · Assignments 4 and 5

Harvard ATG course HPC

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.

Optional but recommended

AWS

Run a small deployment on an EC2 instance if you want one; no GPU is needed. Register the account with the course, protect the endpoint, set a billing alarm before launch, and stop the instance when you are finished.

Assignment by assignment

Work	Use	Why
Assignment 1	Claude Code + AWS or CloudLab	Build with the course agent account and deploy web app. No GPU required.
Assignments 2 Assignments 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.
Assignments 4	HPC GPU (RTX PRO 6000 Blackwell)	You serve the model yourself. Use the course `gpu-cs2680` partition.
Assignments 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	HPC by default; CloudLab when necessary	Use the HPC for model and GPU work. Use CloudLab only when the research question depends on bare-metal control or isolation.

If a project needs hardware that neither environment provides, ask the instructor while the scope can still change. Compute can sometimes be arranged; last-minute capacity cannot be promised.

Five rules for every machine

Keep secrets out of agent sessions. A transcript can contain files the agent read and output its commands printed, not just your prompts. Follow the scan-before-you-archive checklist every time.
Configure telemetry on each machine. The course settings live in ~/.claude/settings.json. Your laptop, the HPC, and an EC2 instance each need the telemetry block.
Name the system behind every result. Report the GPU, driver, serving engine and version, model, and workload. Latency or throughput without that context cannot be reproduced or compared.
Release idle resources. Exit the Slurm job, stop the EC2 instance, and terminate the CloudLab experiment. Shared hardware and paid instances should never sit idle by accident.
Escalate access problems early. An account problem in week one is fixable. The same problem on the due date is still an account problem, not an extension plan.

Computing Resources You will Use

Assignment by assignment

Five rules for every machine

Related