1,749 mentions · 790 chunks · 131 episodes
An interesting pattern: using LLMs to astroturf content in an ecosystem. The challenge of an ecosystem is not so much the hill climbing of quality, it's the creation of the ecosystem t...
...prone. Even if it works 95% of the time, that 5% it doesn't is hard to predict. LLMs are great at answering a specific, unique question… but then the user needs to sit there and wait while the answer unspools. Some use cases get enoug...
Another puzzle of LLMs: they're surprisingly bad at generating very large legal JSON blobs. They'll often miss a comma or a } or ]. This breaks our mental model; they're so...
...ore likely a non-viable thing is detected. Tests get more important... and also LLMs make them considerably easier to write.
... in the same direction they've established for a decade, now using the power of LLMs behind the scenes to increase their search quality. This model can create user value. But it has a low ceiling, because the app model presumes a priv...
LLMs can't be trusted with private data or data that might try to prompt inject them. But imagine a set of tubes that by construction can only be combined...
A few fun use cases for young kids and LLMs that some friends shared with me. When driving somewhere with a kid in the car, ask ChatGPT, "Tell me about gas giants" and then help the kid ask fol...
LLMs don't do deep reasoning. They do superficial detail matching crazy well. But it turns out that a huge number of superficial details, if generated by ...
...learned the power of framing, montage, and other dynamics unique to film. Using LLMs for human-like tasks is like recording a stage play. What kinds of non-human-like tasks will LLMs be good at?
LLMs can be used as an intelligent lorem ipsum creator. Lorem ipsum is placeholder text used when mocking up print layouts. It used to just always be the ...
Apps are hard. LLMs are soft. LLMs aren't going anywhere, they're a new fundamental primitive. Everything hard will need to melt to interact with the softness of LLMs. A...
Even with LLMs doing note-taking all the time, it still doesn't create tons of value. Part of the value of note-taking is transmitting the information into the futu...
LLMs are not open-ended. (At least in current architectures) They are crystallized at a moment in time; after they are trained, they do not change or adap...
A sweet spot for LLMs: conceptually easy, syntactically hard.
... platforms who have signed deals to allow their user's data to be used to train LLMs. A bargain common in the same origin paradigm: "give me your data in exchange for getting this service for free." What if it were possible for us as ...
Engineers try to force LLMs to behave like normal computers. The entire reason they're so useful is that they're not normal computers. They're unruly, squishy computers. Lean in...
...e who said they didn't trust confidential computing. Confidential computing and LLMs are both technologies that are useful ingredients, imperfect though they may be, to iterate towards something better. If you were a security absoluti...
If you ask an expert if LLMs are good at a task, they'll say it's insufficient. But what you should do is ask the person who isn't good at the task if it's better than them! You ...
LLMs aren't just fluent in English, they're fluent in all languages in their training set! Spanish. JSON schema. Mermaid diagrams. A universal babelfish!
The pipeline of reasoning that powers society… and LLMs. The vast majority of "reasoning" is actually a fuzzy interpolation of previously cached answers. The caching is not just in a single brain, but in t...