LLMs are great at handling exceptions.
LLMs are great at handling exceptions. Look at recurring exceptions over many users, or over a day or so, and then bundle them up, and then have the LLM f...
Topic: llms
1,841 mentions · 834 chunks · 141 episodes
194.1× distinctiveness vs baseline
?
How much more common this term is here than in ordinary English. Higher values mean the topic is more characteristic of this corpus.
1.6x burst in 2025 Q1
?
Peak quarter intensity across the topic's active span. Higher values mean attention was concentrated into a shorter stretch rather than spread evenly over time.
Topic summary
?
A short read on the topic's time range, peak episode, and strongest associations. Use it as the quick orientation before drilling into examples.
- llms appears in 834 chunks across 141 episodes, from 2023-11-06 to 2026-10-12.
- Its densest episode is Bits and Bobs 10/20/25 (2025-10-20), with 17 observations on this topic.
- Semantically it travels with Claude, ChatGPT, and Meta, while by chunk count it sits between Claude; its yearly rank moved from #2 in 2023 to #1 in 2026.
Over time
?
Raw mentions over time. Use this to see absolute attention, not relative rank among all topics.
Observations
?
The primary evidence view for this topic. Sort it chronologically when you want concrete examples behind the larger pattern.
Software was always an evolving, almost living thing.
...ise engineers who liked to write that would point it out. But now in the age of LLMs it is becoming increasingly self-evident. The environment must always be changing, so thus the software must always change. This means that "The last...
What if we had self-writing prompts?
... prompts?[b] Writing a good prompt requires LLMfu. It requires knowing what the LLMs can do, and how to avoid pitfalls. A self-writing prompt can take a short utterance from a user, expanded by understanding your context and the best ...
The New Yorker: What If We Can Never Trust A.I.?
...ever be perfect. The question is what imperfections we're willing to tolerate." LLMs will never be perfect oracles, and that's OK. We should design scaffolding around them that works well even when the model isn't perfect.
My friend Ben Follington: "For cooking, models act like a chef but are actually just nerds for cookbooks."
...ll recommend a song and I remember 'oh you don't actually know what music is.'" LLMs can do a convincing job of acting like they understand experiential phenomena, but they only have ever seen the shadows in the cave.
LLMs don't necessarily help you think 10x deeper.
LLMs don't necessarily help you think 10x deeper. They allow you to fill in the details you wouldn't have previously had the patience or time to do. The f...
LLMs are great at finding zero days not because they're smart but because they're parallelizable.
LLMs are great at finding zero days not because they're smart but because they're parallelizable. It's not that they're smarter than a human security rese...
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.
...for even the swarm of experts to find. This is the state we're in with applying LLMs to useful work.
Implied assumptions are dangerous.
...flict without either party proactively realizing it. This can happen often with LLMs and agents. If a system makes assumptions that the other party might not share, it should proactively state them, so the other party can call them ou...
For multi-agent setups, "The agent is yours alone" and "the agent is global" are easy.
...l your knowledge base, the more dangerous it is to share. Slack bots powered by LLMs that can be called by coworkers are aimed at teams with significant amounts of pre-existing trust.
We're stuck on a local maxima of software.
...terests, and the amount of the software is a tiny fraction of what it could be. LLMs is leading to a renaissance in software. Now is the time to escape that local maxima.
I wonder if we could find novel algorithms within LLMs' weights.
I wonder if we could find novel algorithms within LLMs' weights. Even back in the Claude 2 days, the interoperability research could see Claude replace memorized facts about numbers with the algorithm for...
How can you make your data work for you?
...o not just lie around, but do things for you? We have pixie dust in the form of LLMs, but if you sprinkle it recklessly it might be like the Sorcerer's Apprentice. Imagine prompt injection as the brooms getting confused and drowning y...
The last era was dominated by the Generic Technocrat.
...ideas happen by executing competently on the piece they were an expert in. Now, LLMs provide super-human competent, consensus work to everybody for basically free. The next era will be owned by the Distinctive Generalists. The people ...
Overheard: "Silicon Valley in the age of LLMs feels like being in the Renaissance in Florence."
Overheard: "Silicon Valley in the age of LLMs feels like being in the Renaissance in Florence." There does feel like a sense of "we can do anything" joy with a sense of uh-oh of "nothing we did b...
Would you buy a critical product from a cult?
...The question is: do they have power over what you think or not? If you're using LLMs to answer questions, you have to care a lot about the bias of its creators. If you're using LLMs to distill mechanistic code, you have to care a lot ...
Gallows humor tweet: "sandboxes are just escape rooms for llms."
Gallows humor tweet: "sandboxes are just escape rooms for llms."
Reward-hacking isn't just a thing LLMs do.
Reward-hacking isn't just a thing LLMs do. Humans do it too. It emerges any time the agents don't care about the why but only the what. Reward-hacking is Goodhart's law. Reward-hacking wil...
Robots seem like they'll be less socially disruptive than LLMs will be with knowledge work.
Robots seem like they'll be less socially disruptive than LLMs will be with knowledge work. The reason comes down to atoms vs bits. Bits can diffuse at the speed of light, in the limit. Atoms diffuse many orders ...
Kevin Kelly's excellent new piece: Latent Space as a New Medium.
Kevin Kelly's excellent new piece: Latent Space as a New Medium. The ability of LLMs to hold an engaging conversation is a distracting party trick. We've reduced all of human knowledge into a hologram that can fit into a cluster of GP...