blakestacey @ blakestacey @awful.systems

Posts

51

Comments

1,266

Joined

2 yr. ago

Moderating

---

Let's invite Taylor & Francis to the party. This book chapter has a "results" section that reads like the whole thing came out of GlurgeBot, with the beginning clumsily edited to hide that fact:

An AI language model do not have access to data or specific research findings. However, in a research paper on advancing early cancer detection with machine learning, the experimental results would typically involve evaluating the performance of machine learning models for early cancer detection.

I don't know why the Journal of Advanced Zoology would be publishing "Lexico-Stylistic Functions of Argotisms inEnglish Language", but there you go:

I apologize for the confusion, but as an AI language model, I don't have access to specific articles or their sections, such as the «Introduction» section of the article «Lexico-stylistic functions of argotisms in the English language». I can provide you with a general outline of what an introduction section might cover in an article on this topic

From a couple weeks ago:

I'm doing a reading of good fan-fiction at a con this weekend, to counter the many "bad fanfic reading" panels. I want to read an interesting passage from HPMoR

And Wiley:

Certainly, here are the formulas for calculating accuracy

I'm happy for you / or sorry that happened

And IEEE!

As an AI language model, I don't have access to the specific results and findings of any particular research study. However, some general guidance is provided on how a research study should report and discuss its findings. In general, the results section of a research study should provide a clear and concise presentation of the data and findings. This can include tables, figures, and statistical analysis to support the results. The discussion section should then provide a more detailed interpretation and explanation of the results, including any limitations of the study and implications for future research.

Also this:

As an AI language model, I cannot determine how good your results are without more context.

Oh boy, I have thoughts about Kolmogorov complexity. I might actually write a section in my textbook-in-progress to explain why it can't do what LessWrongers want it to.

A silly thought I had the other day: If you allow your Universal Turing Machine to have enough states, you could totally set it up so that if the first symbol it reads is "0", it outputs the full text of The Master and Margarita in UNICODE, whereas if it reads "1", it goes on to read the tuples specifying another TM and operates as usual. More generally, you could take any 2^N - 1 arbitrarily long strings, assign each one an N-bit abbreviation, and have the UTM spit out the string with the given abbreviation if the first N bits on the tape are not all zeros.

Oh look, here's MDPI doing the same thing:

Certainly, here is the revised paragraph:

By solving Equation (8), ...

And also here:

Certainly, here are some additional points for further evaluation and observations regarding the topic of green hydrogen integration into the energy future

something something a cause hole

In February of 2021 the far-right social media platform Gab experienced a data breach resulting in the exposure of more than 70 gigabytes of Gab data, including user registration emails and hashed passwords. Like many of those on the far-right, Red Panels had a presence on Gab, so we consulted the now-public data set from the Gab exposure. We learned that the “@redpanels” account had been registered with the email hgraebener@*****.com.

womp womp

Yeah, I hung out a lot in Internet skeptic/atheist circles during the 2005-10 era, and as far as I can recall, the overlap with LessWrong, Overcoming Bias, etc., was pretty much nil. This was how that world treated Ray Kurzweil.

Aella : birthday orgies :: Yudkowsky : fanfiction

"There once was a dildo so long, sold in a set with a bong, I forget the resht Trebek but your mother's a whore"

The spread of the parody chart led to jokes about what "came in a fluffer" could mean in a business context. For example, on March 4th, Martin Shkreli joked

Fuck this, launching myself out of the Universe

No, for good or ill.

(I forget where I learned about that list, but it makes for interesting reading.)

Oh my Glob that's on her Wikipedia page

(raised hand of disapproval) slut-shaming

(pointing finger of approval) Substack-shaming

Inside the Strange World of the Uwu Smol Beans: An Exposé of a Quirky Community with No Racists Whatsoever

We should have known the English rain was trouble when it started giving people tans

Yet another news story that omits how the science in HPMOR, the Sequences and the flagship e/acc blog is just wrong. Like, failing junior-high biology wrong.

The A.I., trying to access a Web site, was blocked by a Captcha, a visual test to keep out bots. So it used a work-around: it hired a human on Taskrabbit to solve the Captcha on its behalf.

Wait, didn't that turn out to be bullshit?