1,841 mentions · 834 chunks · 141 episodes
LLMs can look at many different emails that you missed the details in because you got bored. A power of infinite patience! These can help assist you with ...
... but go to a different source you'll get a different answer. The monoculture of LLMs leads to everyone having the same answers to the same questions.[ck] I heard of someone who thought someone else had plagiarized their essay. Turns o...
This week's round up of "we're in the wild west era with LLMs": A postmortem for a vibecoded tool called DrawAFish that had abuse problems. A Cursor exploit that allows arbitrary remote code execution. AgentFlay...
The most important ability of LLMs is infinite patience. What kinds of information tasks could normal humans do if they never got bored?[cy]
LLMs can be infinitely sycophantic. But if they aren't, that's bad too, because you have to trust its motives and the motives of who created it to be alig...
...context as possible, you want the right context. The wrong context confuses the LLMs and makes them spiral out of control, losing the plot. What you want is the smallest amount of context that will give the LLM what it needs to give y...
The question is not, "how to do cool open ended things with LLMs." That's easy. As a chatbot, it's trivial. As a thing that can do tool use (and possibly have side effects), it's easy to do for enthusiasts who are ...
Imagine a system where LLMs generate new combinations that a community of humans curate emergently through their individual authentic actions. LLMs help create "patterns": littl...
...ever took off outside of niche applications. Maybe that changes in the world of LLMs?
...y code. If you're a curated programmer you'll get a lot of curated code. Before LLMs, sloppy programmers could at least make a lot of progress, which was an advantage. But now the LLMs do that part for free and for everyone. The balan...
Don't let LLMs make load-bearing security decisions.
Anthea's newest piece compares LLMs as freeing a caged tiger. The thinker is a caged tiger set free with intellectual collaborators willing to go wherever you want to go. A cage is also...
...people making real decisions that align with their authentic needs and context. LLMs are a fossilized version of real people's decisions; it can't pick something novel. It looks superficially the same, but it's fundamentally different...
...r of exceptional people over a larger number of merely competent people. Before LLMs, many execution tasks required a human, so you needed bodies. Now exceptional employees can have more leverage.
LLMs are like water. They dilute anything you add them to. If you give them something already boring, it gets more boring. But if you give them juice conc...
...atabase to a real consumer need requires lots of complex specialized stuff. But LLMs might not need that. It's kind of weird that the LLM model creators also have consumer frontends to them. It shows how powerful LLMs are that they ca...
...tors. These are extremely hard to bootstrap, even if they're very powerful. But LLMs are infinitely patient, always game to do whatever you put them up to. LLMs can now be your eager first collaborator, making it much easier to get th...
...en the actual LLM-native software yet. The software that takes for granted that LLMs exist, not as the primary input, but as a secondary one.
Code is cheap to build, expensive to have. This is even more true in a world of LLMs. YAGNI.
There is no solution to prompt injection in systems where LLMs call the shots. LLMs seeing raw data and being asked to make load-bearing security decisions cannot be made safe, no matter how good the model gets. ...