Could and should are distinct.
- Could and should are distinct.
- There are things that LLMs could do that you shouldn't do.
From other episodes
- My friend Ben Follington: "For cooking, models act like a chef but are actually just nerds for cookbooks."2026-08-03
- LLMs don't necessarily help you think 10x deeper.2026-08-03
- LLMs are great at finding zero days not because they're smart but because they're parallelizable.2026-08-03
- If you, a non-expert, can come up with an effective workflow that an expert is surprised by and thinks is interesting then it implies the ecosystem is in the early stage.2026-08-03
- Implied assumptions are dangerous.2026-08-03
- For multi-agent setups, "The agent is yours alone" and "the agent is global" are easy.2026-08-03
- We're stuck on a local maxima of software.2026-08-03
- I wonder if we could find novel algorithms within LLMs' weights.2026-08-03