เกี่ยวกับตอนนี้
TL;DR: Increasingly when you interact with frontier models, your prompt doesn't only contain the words on the page, but also a lot of what you've ever publicly written online.
This is not intended to be a scary post. And I'm not going to suggest that you self-censor (and honestly, by the time you're reading this, it's kinda too late anyhow).
But it is something that's underappreciated and would be good for more people to be aware of and even proactively address with their models.
Latent space fidelity has improved
Modern transformers which power large language models (LLMs) take a very large amount of information in their training data and condense many different aspects of that data into a coherent structure, and this representation of that compressed knowledge is generally referred to as their "latent space."
Latent space is not uniform and varies across models. A small model like Claude Haiku might have worse recall for the details of a late bronze age peace treaty than a model like Claude Fable. In fact, I’ve had a few benchmark questions around unintuitive details in various texts which historically models were unable to recall that have suddenly been able to be [...]
---
Outline:
(00:49) Latent space fidelity has improved
[... 6 more sections]
---
First published:
October 14th, 2026
Source:
https://www.lesswrong.com/posts/STBuKAX9kkMJunErA/your-prompt-plus-everything-you-ve-ever-publicly-written
---
Narrated by TYPE III AUDIO.
---
This is not intended to be a scary post. And I'm not going to suggest that you self-censor (and honestly, by the time you're reading this, it's kinda too late anyhow).
But it is something that's underappreciated and would be good for more people to be aware of and even proactively address with their models.
Latent space fidelity has improved
Modern transformers which power large language models (LLMs) take a very large amount of information in their training data and condense many different aspects of that data into a coherent structure, and this representation of that compressed knowledge is generally referred to as their "latent space."
Latent space is not uniform and varies across models. A small model like Claude Haiku might have worse recall for the details of a late bronze age peace treaty than a model like Claude Fable. In fact, I’ve had a few benchmark questions around unintuitive details in various texts which historically models were unable to recall that have suddenly been able to be [...]
---
Outline:
(00:49) Latent space fidelity has improved
[... 6 more sections]
---
First published:
October 14th, 2026
Source:
https://www.lesswrong.com/posts/STBuKAX9kkMJunErA/your-prompt-plus-everything-you-ve-ever-publicly-written
---
Narrated by TYPE III AUDIO.
---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
ภาษาอังกฤษ
สหรัฐอเมริกา
สำเนาบทสนทนา 🔗
Are you the producer of this podcast?
Add a podcast transcript
Need Audio-to-Text?
Transcribe with Listen411 in Just 60 Seconds
ตอนอื่นๆ ใน PODCAST นี้
The Piltdown man was the most successful artifactual hoax of all time. The relevant skull was a chimeric melange of orangutan and human bone fragments from several individuals “discovered” in England in 1912, and meant to represent a transitional form between apes and humans. Given the intense inte…
This is an extremely lengthy post by Nick Cammarata.
Author's summary on twitter:
interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news abo…
Epistemic status: I traced one famous anecdote to its printed source and to both coauthors' own accounts of where it came from. Confident it was never a study. No claim either way about whether quantity beats quality in general. AI use: research (tracing the story to the book, to the coauthors…
David Africa & Nick Levine TLDR We ran several persona experiments on Talkie, a 13B model trained only on English text from before 1931. We ran them alongside its modern twin (same architecture, trained on regular data as a control) and Llama-3.1-8B.
Talkie can generalise maliciously. You can…
ข้อสงวนสิทธิ์: พอดแคสต์และอาร์ตเวิร์คที่ฝังอยู่ในหน้านี้มาจาก LessWrong ซึ่งเป็นทรัพย์สินของเจ้าของและไม่มีส่วนเกี่ยวข้องหรือรับรองโดย Listen Notes, Inc.
