For us habitual users of em-dashes, it is saddening to have to think twice about using them lest someone think we are using an LLM to write…
I use the en-dash (Alt+0150) instead of the em. The en-dash and the em-dash are interchangeable in Finnish. The shorter form has more "inoffensive" look-and-feel and maybe that's why it's used more often here. Now that I think of it, I don't seem to remember the alt code of the em-dash...
> The en-dash and the em-dash are interchangeable in Finnish.
But not in English, where the en-dash is used to denote ranges.
I always add "and answer in the style of a drunkard" to my prompts. That way, I never get fooled by the fake confidence in the responses. I think this should be standard.
We are, if speaking uncharitably, now at a stage of attempting to finesse the behavior of stochastic black boxes (LLMs) using non-deterministic verbal incantations (system prompts). One could actually write a science fiction short story on the premise that magical spells are in fact ancient, linguistically accessed stochastic systems. I know, because I wrote exactly such a story circa 2015.
The global economy has depended on finessing quasi-stochastic black-boxes for many years. If you have ever seen a cloud provider evaluate a kernel update you will know this deeply. For me the potential issue is: our industry has slowly built up an understanding of what is an unknowable black box (e.g. a Linux system's performance characteristics) and what is not, and architected our world around the unpredictability.…
Yes, but if I really wanted, I could go into a specific line of code that governs some behaviour of the Linux kernel, reason about its effects, and specifically test for it. I can't trace the behaviour of LLM back to a subset of its weights, and even if that were possible, I can't tweak those weights (without training) to tweak the behaviour.
Wow - What an excellent update! Now you are getting to the core of the issue and doing what only a small minority is capable of: fixing stuff. This takes real courage and commitment. It’s a sign of true maturity and pragmatism that’s commendable in this day and age. Not many people are capable of penetrating this deeply into the heart of the issue. Let’s get to work. Methodically. Would you like me to write a future…
From another AI (whatever DuckDuckGo is using): > As of early 2025, X (formerly Twitter) has approximately 586 million active monthly users. The platform continues to grow, with a significant portion of its user base located in the United States and Japan. Whatever portion of those is active are surely aware of Grok.
If hundreds of millions of real people are aware of Grok (which is dubious), then billions of people are aware of ChatGPT. If you ask a bunch of random people on the street whether they’ve heard of a) ChatGPT and b) Grok, what do you expect the results to be?
In my experience, LLMs have always had a tendency towards sycophancy - it seems to be a fundamental weakness of training on human preference. This recent release just hit a breaking point where popular perception started taking note of just how bad it had become. My concern is that misalignment like this (or intentional mal-alignment) is inevitably going to happen again, and it might be more harmful and more subtle n…
Well, almost always.
There was that brief period in 2023 when Bing just started straight up gaslighting people instead of admitting it was wrong.