gnarlouse

Honestly, you're right.

Imagine implanting a lithium ion battery in your head

My only feedback is $49 for AI slop feels like extortion at best, and delusion at worst. Don't give up building stuff, we should all be using AI to build ideas because the cost of developing them has dropped substantially. We should not be using them, however, to grift one another.

These articles are useless because where is the search bar that lets me plug in my make/model and look at the specific results like cool research guys thanks for burying the lede in 3000k words

If a 15yo can find it

If you flip "dots" over, it kind of looks like "stop" which is precisely how I feel about this project.

This reminds me of decades ago when ...wait, I was still writing code like three years ago.

I enjoyed the book, but I "read" it on Audible which was possibly not the ideal experience. It was kind of fun though, they had static crackling for all the redacted bits.

I love stuffing eldritch horror inside a teddie bear plushie. So perfectly a caricature of modern tech-dystopianism.

God I want the fucking market to crash

Slop detected

Smoked Metas

you want smaller models with comparable capabilities. for resource efficiency, market efficiency, environmental conservation.

Hideous

At least capitalism isn't at the center of the most impactful technological revolution in human history.

Does that mean Verbesserschlimmung is "improving things for nothing" because the same can be said of AI.

YO (AIDR)IAN!

Why would you make this. I feel traumatized.

It's YOUR fault! I knew it had to be one of us. Now I know. At least you were honest about it.

If there's a real existential pressure on a certain group of engineers, those that escape with their employment will carry evolutionary DNA with them (along with a substantial helping of pure luck) in the form of experience. Those that don't will disappear.

Nothing else this article says matters much in my opinion. If you're concerned about something, do something about it.

AI is still just a tool.

> NEVER

with critical thought*

fixed that for you, only sith's (and unreasonable people) deal in absolutes; you almost did!

this might be the only comment on this post worth reading, much less the article...

seems like a petty easy construction, proof engagement kinda thing

Isn't there a clause to opensource for "unmaintained, delivered as is?"

It's a stupid word soup on second read, but hey, it works, and that's all that matters with "stochasty the parrot."

""" In this project, I require a socratically delivered line of conversation. Here's the typical structure to the conversation. I ask some question. You need to factor and reason about how to conduct and deliver a conversation. Best practices would be to limit terminology, or assess with the user whether they have a firm grasp on terminology before you use it. You must be very strict about this, it's unacceptable to just introduce a new concept, actor, phrase or other complication into the conversation without first labeling who what or why it exists for the conversation.

Conversation structure needs to be front-loaded with a brief interview for the user, "you understand X?", "whats your understanding of Y?".

Conversation structure then needs to proceed with single-sentence questions from the agent. User replies with an answer. Sometimes the agent needs to correct the user, but only ever do so with yet another question. """

^^ these are the instructions I have installed at the root of a "project".

Keep in mind, this is claude opus 5 low effort we're talking about, in the "projects" area of the mobile app. Here's the process I use to set up its knowledge:

1. I take screenshots of the textbook on my iPhone, and upload a chapter at a time.

2. I have it summarize the chapter into markdown by analyzing screenshots. You could probably achieve this simpler, if you just had the textbook in PDF.

3. I walk with my boy Clau-crates.

I've done this for a couple of weeks and haven't seen it revert back into its typical context-dumping behavior.

On second read, there's probably some clean up I could do. Thanks for making me pull it out and look at it. Things that could probably be improved:

- tell it to cross-check resources online to further ground itself

- use simple, short sentences (long sentences make the brain blur a bit)

- not be sycophantic (it seems like project mode has discarded with my root-level anti-sycophancy prompt)

Sorta. If its response is grounded in actual material, and you're thorough, it's not so risky. As with all learning, trusting one source is a risk in itself. Hell, I didn't even trust my physics textbooks in college. Physics.

I've had success using the socratic method. I give Claude some topic (say, how the intricacies of the bond market works, the content from which are screenshots of pages from a textbook), and then I go on a walk chatting with it in voice mode. Claude is the expert, I am the student. Claude asks me questions, leading me to an answer logically. I come back with questions, and we back and forth. LLMs arent like they were in '23-'25. I'm almost always skeptical its going to lie, and almost always wrong.

In particular:

- I limit it/encourage it to give me single sentence questions

- I sometimes will ask it to tell me a motivating, human-grounded story, when we're starting a new concept: claude responds "Maya is a bond portfolio manager, and her boss has asked her to quickly price in what happened if yields go down. She knows her bond's average duration, a measure in time, but she doesn't have a percentage, which is what her manager wants. How can she give him a percentage number with just a duration figure and the proposed new yield?"

- I'll often ask claude to let me work through it, to derive the thing myself, often resulting in a string of thoughts with "yes/no" trailers, to get the LLM to reply yes or no only, and avoid derailing my train of thought. If yes, my train of thought keeps going. If no, I've got something wrong.

- I'll sometimes stop and have it craft an artifact. I typically say "build me a Brilliant.org-style interactive demo of the topic", especially when we get into the realm of looking at the actual maths of a thing (for which prose and dialog is not optimal by itself AFAICT)

- I'll do this while I'm traveling, while I'm walking, while I'm doing chores.

It's so much fun.

Why are you booing me I'm right

i do actually think the general thrust of the idea is good. i also think it's sort of inherently cursed, and has some amount of a predeterminable fate.

if it doesnt take off, it dies.

if it does take off and becomes a relevant currency of some sort, it will need improving. if it needs improving how far are we willing to go? does some alternative system fork off to handle severity of provenance concern?

what happens when AI action becomes indistinguishable from human action? what happens when sticking computers in your head becomes vogue?

if it takes off and fills a small niche, maybe thats the best future.

Like I said, cool idea, but seemingly very cursed from the get go.

If the US AI market collapses, the entire US economy collapses.

Anybody can ELI5?

Honestly even just a bookmarking system would go a long way to fix the problem, but getting "off-topic" in LLMs (3 years later and trillions of dollars of investment) still ruins my flow entirely. I end up playing an unwanted game of scrollbar warrior jumping back and forth between two points in chat. Could be that I'm studying a textbook and looking to enhance/check my understanding with Claude, or that I'm working on complicated tasks in my codebase. Side tangents always crop up. LLMs don't handle it well. Blows my mind that it doesn't bother anybody else, perhaps IATAH