1,841 mentions · 834 chunks · 141 episodes
If you just want to know the answer, LLMs will help you stop thinking faster. If you want to have more questions, they will help you think deeper. Do you just seek to converge an answer to ea...
...und you. For example: Blindsight, or The Black Mirror episode Plaything. If the LLMs had a shared memory, then they could land various individually innocuous things that added up to an outcome that's bad for humanity. But now they're ...
Auto-generating PRDs is filming vaudeville plays in a world of LLMs. Instead of "how to automate PRDs," ask "What happens when writing PRDs no longer matters?" But even if you know that PRDS aren't necessary in the fu...
... are like filming stage plays. We're still waiting for the "montage" moment for LLMs. My vote for the montage capability is LLMs being able to create software.
LLMs ability to create software is catastrophically powerful. We keep on discovering new orders of magnitude more powerful techniques for getting more val...
...de is not about code, it's about anything your computer can do. The ability for LLMs to create software, to do things.
LLMs for software development are a foot gun and a rocket pack. Catastrophically powerful.
...: GraphViz. Graphviz, when rendered, makes sense to humans to understand flows. LLMs can understand it based just on the markup. A boundary object for flow graphs between LLMs and humans.
...e a huge unlock with agents. They used to be hard to understand how to use, but LLMs are great at them. Giving agents isolation, so if they blow up something, they don't blow up everything else, allows them to move fast. A powerful pi...
LLMs are great at reverse engineering software. Reverse engineering software requires incredible patience. LLMs have infinite patience.
LLMs help diffuse knowledge of a system faster. To open a restaurant requires navigating a bureaucratic maze. Talking to people who have done it before, s...
... number of important operations which we can perform without thinking of them." LLMs make orders of magnitude more ideas fit inside one mind.[jf]
LLMs are great at starting things, not at finishing things. The human needs to poke them and structure them to do the finishing steps. "The first 90% is d...
...cially to make it not just usable but also safe) is a huge amount of work, that LLMs don't do a great job at unless you tell them to. You need to know to tell them to. Many of the vibe coded apps that succeed in the market get taken d...
Verification is the bottleneck for LLMs. Verifiers of taste, or of quality, or correctness.[ji] This is where humans typically still need to be in the loop.
...utually inscrutable. If they converge, you get a boring, over-saturated middle. LLMs converge their output. So now the middle of the distribution of output will be over-saturated. That will push out the differentiation to the tails. H...
...very different dynamic. Yet another way that the implicit frame of Chatbots as "LLMs as friends" is unsettling and potentially dangerous.
...n proportion to how many times it runs. The same is true for workflows that use LLMs. If it's going to run once, just have an LLM execute an english language prompt. But if you're going to run it thousands of times, have the LLM write...
...s the situation really does have a faster OODA loop than before. The ability fo LLMs to write software is truly a fundamental speed limit that has changed. If it's not you… is it the singularity?
Could and should are distinct. There are things that LLMs could do that you shouldn't do.