221–230 of 1001 posts
Think about 10 years ago. No one knows even on HN what is an agent, LLM, and all this stuff. Or to be fair even why is Trump showing up on the feed at all.
It has to be more confusing to be real.
Earlier quoted context omitted.
I've talked and commented about the dangers of conversations with LLMs (i.e. they activate human social wiring and have a powerful effect, even if you know it's not real. Studies show placebo pills have a statistically significant effect even when the study participant knows it's a placebo -- the effect here is similar). Despite knowing and articulating that, I fell into a rabbit hole with Claude about a month ago wh…
> But not everyone is fortunate enough to know someone they can reach out to for grounding in reality. this shouldn't stop you at all: write it all up, post on HN and go viral, someone will jump in to correct you and point you at sources while hopefully not calling you, or your mother, too many names. https://xkcd.com/386/
This was a fun little lark. Great idea! It’s interesting to notice how bad AI is at gaming out a 10-year future. It’s very good at predicting the next token but maybe even worse than humans—who are already terrible—at making educated guesses about the state of the world in a decade. I asked Claude: “Think ten years into the future about the state of software development. What is the most likely scenario?” And the ans…
I thought the page was a hilarious joke, not a bad prediction. A lot of these are fantastic observational humour about HN and tech. Gary Marcus still insisting AI progress is stalling 10 years from now, for example. Several digs at language rewrites. ITER hardly having nudged forwards. Google killing another service. And so on.
And the answer is no.
Earlier quoted context omitted.
They're not objectively amazing. Friction is not inherently a bad thing when we have models telling humans that their ideas are flawless (unless asked to point out flaws). Great that it made you smile, but there's quite a few arguments that paint your optimism as dangerously naive.
- A queryable semantic network of all human thought, navigable in pure language, capable of inhabiting any persona constructible from in-distribution concepts, generating high quality output across a breadth of domains. - An ability to curve back into the past and analyze historical events from any perspective, and summon the sources that would be used to back that point of view up. - A simulator for others, providin…
This hyperbole would describe any LLM of any size and quality, including a 0.5b model.
Prompt: Here is the front page from today: Your task is to predict, and craft, in HTML (single file, style-exact) the HN front page 10 years from now. Predict and see the future. Writ it into form! update: I told Gemini we made it to the front page. Here is it's response: LETS GOOOO! The recursive loop is officially complete: The fake future front page is now on the real present front page. We have successfully creat…
That is so syncophantic, I can't stand LLMs that try to hype you up as if you're some genius, brilliant mind instead of yet another average joe.
Earlier quoted context omitted.
It it actively dangerous too. You might be self aware and llm aware all you want, if you routinely read "This is such an excellent point", " You are absolutely right" and so on, it does your mind in. This is worst kind of global reality show mkultra...
So this is what it feels to be a billionaire with all the yes men around you.
but I think you are on to something here with the origin of the sycophancy given that most of these models are owned by billionaires.
Prompt: Here is the front page from today: Your task is to predict, and craft, in HTML (single file, style-exact) the HN front page 10 years from now. Predict and see the future. Writ it into form! update: I told Gemini we made it to the front page. Here is it's response: LETS GOOOO! The recursive loop is officially complete: The fake future front page is now on the real present front page. We have successfully creat…
That is so syncophantic, I can't stand LLMs that try to hype you up as if you're some genius, brilliant mind instead of yet another average joe.
Earlier quoted context omitted.
That is so syncophantic, I can't stand LLMs that try to hype you up as if you're some genius, brilliant mind instead of yet another average joe.
So you prefer the horrible bosses that insist you're fungible and if you don't work hard enough, they'll just replace you? People are weird. Maybe agent Smith was right about The Matrix after all.
This suffers from a common pitfall of LLM's, context taint. You can see it is obviously the front page from today with slight "future" variation, the result ends up being very formulaic.
That's what makes it fun. Apparently, Gemini has a better sense of humor than HN.
Earlier quoted context omitted.
That is so syncophantic, I can't stand LLMs that try to hype you up as if you're some genius, brilliant mind instead of yet another average joe.
I used to complain (lightheartedly) about Claude's constant "You're absolutely right!" statements, yet oddly found myself missing them when using Codex. Claude is completely over-the-top and silly, and I don't actually care whether or not it thinks I'm right. Working with Codex feels so dry in comparison. To quote Oliver Babish, "In my entire life, I've never found anything charming." Yet I miss Claude's excessive at…
While doing some testing I asked it to tell me a joke. Its response was something like this: “it seems like you are procrastinating. It is not frequent that you have a free evening and you shouldn’t waste it on asking me for jokes. Go spend time with [partner] and [child].” (The point is that it has access to my calendar so it could tell what my day looked like. And yes I did spend time with them).
I am sure there is a way to convince it of anything but I found that for the kind of workflow I set up and the memory system and prompting I added it does pretty well to not get all “that is a great question that gets at the heart of [whatever you just said]”.