1,690 mentions · 755 chunks · 125 episodes
...itive labor, they just required humans to do a new kind of cognitive labor. But LLMs can now truly handle it. But only if they have the context of your life and you trust them to act as an extension of you.
Some terminology: A harness is mechanistic code that LLMs run within. An agent is a loop with an LLM and tool calls. An assistant is an agent with a memory.[b]
LLMs are really good at rebasing.[c] Rebasing normally is tedious and error-prone. A form of cognitive labor that dominates the development of software. B...
LLMs are easy to trick by putting words in their mouths. If you give an LLM a task like "Write a poem about Strawberries" and then prefill its answer with...
...ade any data. A much larger surface area! All data can do things now, thanks to LLMs. Powerful, but catastrophically dangerous in our current physics of trust.
LLMs are significantly cheaper if you only append the tokens. If you only append tokens, you can reuse the existing KVCache from earlier runs instead of h...
...ready released a completion API. The amount of value that can be extracted from LLMs is extremely variable in different verticals. A general-purpose API has to be priced at the median amount of value across verticals. But the amount o...
If you're below mean on a given dimension, LLMs pull you up. If you're above, LLMs pull you down. Your own ability is not the global average. Your skill might be below the average quality, or above...
LLMs don't have an experience for others to resonate with. LLMs are static and unable to learn. Also, they're a view from nowhere. That makes them hard fo...
...if there were demand. That was because building products was expensive. But now LLMs make it trivial to make real software quickly. So now you can make a bungalow in the jungle to check for demand!
It's not a random happenstance that LLMs love filesystems and bash. Unix has three key design concepts: 1) Everything is a file[c]. 2) Commands should do one thing well. 3) Pipes connect dif...
... want to automate, you have to either add structure or add intelligence. Before LLMs, the former required humans to do the structuring. Before LLMs, the latter was impossible. Now you can do both!
... tied to that community. Of course, that also doesn't matter that much, because LLMs are so insanely good at translating from one domain to another.
... used to be too much of a pain to extract our data into other services. But now LLMs could plausibly do the cognitive labor given a Google Takeout dump. The thing that would be hardest to leave is changing your gmail address for thous...
...k matter star at the semantic center of the definition of the software. But now LLMs can translate from anything to anything. For the first time it's possible to have that meta-boundary-object of the actual software definition, in a l...
LLMs do the gilding better than the fundamentals. Which makes sense; they're optimized for the superficial results. Quality is harder to judge than surfac...
When talking to LLMs you don't have to clean up your typos or worry about rambling or bouncing all over the place. It's 100x lower difficulty than writing for another per...
... how it evolves and moves. Humans are absurdly sensitive to this dimension… and LLMs perhaps even more so, since they can do it at a scale humans can't. Humans live in linear time experientially in the moment, by requirement. LLMs liv...
LLMs are like a car. Whenever you want to go, it will take you. LLM helps you be productive but if it's self referential it escapes the ground truth. If y...
...re accomplishes? If the former, then your business is now worth much less given LLMs. If the latter, then there's no problem, and it's possibly even good.[w][x]