What's the difference between a process and a thread?

A process is an independent program with its own memory space; a thread is a unit of execution that lives inside a process and shares that process's memory with sibling threads. Creating a process is heavier (new address space); creating a thread is lighter (shared address space). Threads communicate through shared memory, which is fast but requires synchronization to avoid races; processes communicate through IPC mechanisms like pipes or sockets, which are safer but slower.

In CPython the Global Interpreter Lock (GIL) means only one thread executes Python bytecode at a time, so CPU-bound work doesn't get true parallelism from threads. For CPU-bound tasks — number crunching, image processing — use multiprocessing to sidestep the GIL and use multiple cores. For I/O-bound work — network calls, disk reads — threads (or asyncio) are fine, because the GIL is released during the blocking I/O. Rule of thumb: CPU-bound → processes, I/O-bound → threads or async.

asyncio is single-threaded cooperative concurrency: one thread, one event loop, tasks yield control at await points. It shines for high-concurrency I/O — thousands of simultaneous network connections — because there's no thread or process overhead per connection. It does NOT help CPU-bound work, since a long computation blocks the single loop. So the full picture: asyncio for massive I/O concurrency, threads for simpler I/O or blocking libraries, processes for CPU parallelism.