261–270 of 574 posts
Earlier quoted context omitted.
It’s a reference to Bernard Shaw, who once said that if we ever created a truly artificial mind it would be inside a turtle’s shell. Sturgill Simpson covered the track on his seminal work, Xeno’s Paradox.
Might be a reference to the story at the beginning of A Brief History of Time, attributed to Bertrand Russell’s audience member. Full story in the book
OTOH, I am curious if there's a "practical value" to this exercise? If the LLM already contains the information and implementation knowledge to implement the networking stack inside an FPGA by itself, what value do I gain by learning about HDL, TCP, the bespoke Xillinx tooling, reading the documentation, reading papers on the implementation and going through every bit of details and theory. I feel like there's a meta skill that is more worthwhile for "practical value".
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…
can you share ane example of one of your prompts? I have tried to convert some text into the socratic method and haven't succeeded yet.
""" 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)
I thought LLMs were a great tool for learning new topics - perhaps even complex ones. But overtime, I have had several frustrations with this. First, I get exhausted reading LLM prose. I really don't want to read anything generated by something like Opus 5 at this point. Second, as I dive deeper, I need a way to organize the information in a useful way as I begin to branch out in many different directions. I have tri…
It's much better to feed the book to the LLM and ask questions as you read along, instead of asking the LLM to basically write a custom book for you from scratch.
Earlier quoted context omitted.
dumb question, but what is the best way to feed the book to the llm? i run into context window limits, or practical limitations of digitizing the book
You need a non DRMd copy of the book. You don't have to feed it all at once, although with a 1M context limit it is doable. A few chapters at a time is enough, in my experience. An easy alternative is using NotebookLM (now Gemini Notebook), and that has worked brilliantly for me, but I haven't tested it for technical topics (for that I like the LLM to create graphs and e.g. interact with Mathematica, so I haven't tri…
These animations are great. I have learnt so many things from LLM's, cross checking things is easy enough, but the hallucinations are really not much of a thing any more (in my experience). When you deep dive on things it does seem to get very wordy sometimes (this is claude anyway). Its taught me flutter and dart without opening a book (with the occasional reference page), set me straight on monads finally, refined…
Hallucinations bring to question what you think you've learned. That's going to cost long-term if you labor under mis-apprehensions until you maybe figure out you learned something wrong.
I thought LLMs were a great tool for learning new topics - perhaps even complex ones. But overtime, I have had several frustrations with this. First, I get exhausted reading LLM prose. I really don't want to read anything generated by something like Opus 5 at this point. Second, as I dive deeper, I need a way to organize the information in a useful way as I begin to branch out in many different directions. I have tri…
human conceptual thinking is very much a multi-dimensional graph, which relies on light "approximate" concepts that are "good enough". LLM AR token generation is extremely one dimensional and doesnt care about the "weight" of the concept behind a token.
LLMs hold billions of parameters in "mind" at once. humans hold like four "concepts".
This is the essential mismatch and the primary reason LLM conversation can be so painful and exhausting.
Explaining this and limiting "concepts" to four at a time tops is one of the very few AGENTS.md / system prompts I always use, and it has proven invaluable time and again.
Thinking traces show how effective this is at forcing the LLM to simplify its thinking.
[edit] Also, myself and nearly all of my peers are struggling to choke down the flaws of LLM tooling along with the benefits. the speed at which LLM adoption is being forced, without truly crafting them into quality tools first, is not ok, and not normal.
LLMs have stirred an inhumane hunger and fear. the tech is fine, but the way tech companies (creators and consumers) are behaving should be deeply questioned.
it's NOT normal. it's not ok.