← All IntelClip / AI ToolsCPUs over GPUs: don't use LLMs for deterministic work
From Notion's Token Town — Sarah Sachs, Notion · ≈16:57
“You don't need an LLM to turn a CSV into a PDF.”
“You definitely don't need an LLM to do deterministic SQL queries.”
“This is where people become token poor very quick.”
What’s in it
- Argues CPUs beat GPUs for many everyday backend tasks
- Warns proprietary AI edges vanish as open-weight models catch up in months
- Flags using LLMs for deterministic tasks as a fast way to burn tokens
Clip transcript
six months, they're probably covered by open weight. So, be prepared now. And the last thing is CPUs over GPUs. Um, we've we've recently launched something at notion called workers. I don't think that the GPU is necessary for every job. A lot of the jobs that we have are actually serving um discrete pieces of code. Like you don't need an LLM to turn a CSV into a PDF. You don't need an LLM to talk to notion tool calls if we have a CLI. You definitely don't need an LLM to do deterministic SQL queries. This is where people become token poor very quick.
Comments
Sign in to comment.
Loading comments…