ChatGPT knows too little about me to be useful.
...information is creepy. Where do I dump my life context in a way that will allow LLMs to work on it? A trusted place just for me, totally aligned with my interest.
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.
The context and the LLM you use should be separate.
...nintentionally. Why might context portability happen now when it didn't before? LLMs are the most intimate technology ever, the stakes have never been higher. The hard part of interoperability is coordinating on schemas, but that prob...
ChatGPT's memory feature refusing to tell you what it knows about you is inherently creepy and lampshades the misaligned incentives.
...gagement-maximizing playbook of Facebook, multiplied by the superhuman power of LLMs. Terrifying!
It's my context, not the model's.
It's my context, not the model's.[nn] I want to be able to bring it to other LLMs, and not have to worry about some company building a dossier on me. I also want to choose what context to include or exclude in a given conversation ...
Infinite content and LLMs can create filter bubbles but for your self-perception.
Infinite content and LLMs can create filter bubbles but for your self-perception. Not only is it finding the content that makes you feel good about what you already believe,[n...
Prompt injection is hard to combat because normal sandboxing doesn't work without a million permission dialogs.
...illion permission dialogs. The stuff you'd use to contain the prompt injection (LLMs) is the stuff that can be tricked by anything you show. Turtles all the way down. "Do you trust this domain to get information from this chat?" This ...
Prompt injection will become more and more of a problem as we use AI for more real things, at scale.
...eason this isn't a big problem yet is that we're just in the tinkering phase of LLMs.
Tool calling is what makes LLMs turing-complete.
Tool calling is what makes LLMs turing-complete. Able to not just say, but do.
LLMs are so noisy that it's hard to figure out the quality of underlying components built on top, because the noise dominates the signal.
LLMs are so noisy that it's hard to figure out the quality of underlying components built on top, because the noise dominates the signal. Did it break bec...
I love Inverting the Socratic Method in the Age of AI from my friend Anthea Roberts.
... teaching method that forces students to have good answers. But in an era where LLMs make answers cheap, the real skill is asking good questions.
Anthea pointed out to me that LLMs should raise teachers' expectations of what students can accomplish.
Anthea pointed out to me that LLMs should raise teachers' expectations of what students can accomplish. One approach to LLMs in education is worrying about the floor. "How would you ev...
One of the biggest challenges of Getting Things Done is distilling a big thing into concrete next actions.
...es of Getting Things Done is distilling a big thing into concrete next actions. LLMs can do that easily!
Hill climbing a moving hill doesn't work.
Hill climbing a moving hill doesn't work. LLMs are moving hills. The models are still improving rapidly. Don't over optimize for their current behavior.
LLM companies are trying to get a premature monopoly on LLMs.
LLM companies are trying to get a premature monopoly on LLMs. We didn't figure out the participatory architecture yet, which is necessary for the early stage of new technologies!
This week I learned about the Scots Wikipedia controversy.
...the web, it formed a larger amount of the LLM context on Scots. That means that LLMs also likely replicate Scots poorly, all because of one weird bottleneck. A similar kind of thing happens in evolutionary biology, a "population bottl...
The algorithms we use to navigate the firehose of infinite content shape how society sees itself.
... the worst timeline." Imagine it for our entire digital lives. If everyone uses LLMs to cothink, the guardrails they have will shape all of society. This analysis shows the power of a centralized algorithm that everyone views the worl...
The whole industry will understand the importance of prompt injection in the next few months.
...n it easily. It's child's play to prevent injection with a bit of escaping. Now LLMs with tool use allow all data to be executable. A massive expansion of threat surface area. So now all of the systems builders are thrust into the wor...
Prompt injection sets the ceiling of potential of LLMs.
Prompt injection sets the ceiling of potential of LLMs. Claude and OpenAI will build integrations into chat via things like MCP. Vibe coders will get stuck making dead end little island apps. Both will ge...
Software rots at a speed proportional to rate of change of other systems it's dependent on.
...n adapt and maintain itself to continue working. This is only possible now with LLMs.
I liked this analysis of LLMs as normal technology.
I liked this analysis of LLMs as normal technology. Normal as in electricity, the internet. General purpose, something you can take for granted.