819 karma · joined October 20, 2022
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.
with critical thought*
fixed that for you, only sith's (and unreasonable people) deal in absolutes; you almost did!
seems like a petty easy construction, proof engagement kinda thing
""" 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)
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.
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.
Say you're studying something: STEM topics, Liberal arts topics, a codebase, a textbook, etc XYZ. You're in the flow of discussing a main topic. Invariably, the main topic is built on top of atomic subelements. For example, discussions about Bonds invariably invoke discussions of Present Value, Yield to Maturity.
The branching is because you have a side query that is a potentially unbounded stack of "wait, but why this?" You highlight a segment of text in the current chat, click a button that pops a new conversation over to the right, and continue your "related but off-topic question." You have both context threads in view at once: the main topic & the side topic. You should be able to do this N layers deep.
The alternative is that you get to play scrollbar warrior in the current regime of LLM-designs. It's not really conducive to deep understanding.
This kind of conversation applies naturally to software development too: "wait, so we're working on feature X/refactor X/bugfix X, but that requires us to answer this subthread. And sure these days Claude Fable can probably do it all with the right harness, but does that mean you _understand_ what it just did?
~~edit~~
wait, are you doing that? Love JUCE btw
Maybe PRs these days need to "test" the human? "Explain how this code works, without AI, or it gets rejected."
The joke, of course, is that I imagine a good 75% of the reviews would be "it's shit."
Let's talk about Billionaire Alignment, Economic alignment, Human alignment.
Classware should be M.A.D. -- in that it shouldnt even happen.
Thanks for my next horror shortfilm plot. Twist: he's the protagonist