Learn With AI

13,083 impressions today. 5 followers 2 weeks ago. 18 now. Replies before posts. Every single day.

@lolnvmtho Hmm what could this mean in the grander scheme of things 🤔

I noticed Gen Z ppl don’t carry umbrellas. They just walk in the rain lol

@jasonkneen I do agree that a lot of his claims are quite overhyped and dramatic, but I do believe things he talks about are definitely important and will be very important in the coming years.

Good god please don't listen to this horseshit. 1. OpenClaw is a ralph loop with messaging it's not f**king the greatest piece of software ever written and there's alternatives like paperclip and nanoclaw and tinyclaw that work as good if not better. 2. You don't have to be burning money like this fool. He's making his on clicks and views and so all this drama is great for his numbers but having a 24/7 workforce that's cost him tens of thousands has lead to him releasting ZERO products over last months. Even his screenshots showed 0 tool use. It's all engagement farming bullshit. But you can choose to follow the fool or listen to people who actually know what they're talking about and aren't farming for likes and replies and horseshit. Up to you I have no skin in the game -- just sick of FUD.

Sleeping at 1am-8am yields profoundly different results than sleeping from 10pm to 5am.

@TheEdPill I have had similar results. Somehow I just feel so much worse when I got to bed past midnight than going to bed at a reasonable hour. I am so much more productive when I am able to turn off my phone early.

@NoahKingJr Hey, we all start somewhere. I am just a 15 year old student trying to share my journey.

people with under 35 followers tweeting:

@AarivKhanna Sometimes AI and tech become a little too much, especially as a 15-year-old student. I like to take a step back sometimes and live in the present.

You’re bored because you don’t do side quests, bro. Life is more than just work and bed rotting. Here are 50 side quests to complete:

@parisrouz What actually is Notion and what are the potential ways I could integrate into my workflow as a student?

Notion has turned into a very overwhelming product.

@kaaaash____ I’m going with the good old touchpad 🙌

Be honest, Left or Right

Wow this is honestly the most relatable post I have seen in a while. As a 15 year old student I experience this every single day. Instead of going out and partying after school I go home, get on X, and dive into the latest AI development. The amount of people I can talk to about this is very limited. It’s a lonely world.

I think one of the biggest challenges when it comes to going hard into using AI is loneliness I am learning all these awesome things and becoming super capable But the set of people that I can really talk to about it is very small Is anyone else having this experience?

@bryan_johnson Sounds like a job for AI 🤔

I've instructed my chef to make meals that are exactly 700 calories. But they're more than 700 calories. You know how I know? My resting heart rate is elevated by 3 beats per minute. I'm 1,000+ reps (days) in knowing how food impacts my heart rate.

For sure, I used to blame Anthropic too until I realized there are a lot of things you change about the way you utilize AI to minimize credit expenditure. Simply editing your last message to Claude if you mess up a prompt rather than sending another should message can conserve credits.

"Claude usage limit reached. Your limit will reset at 7pm" every. fucking. day. was about to pay $200 for Max. then I read this article 98.5% of tokens - wasted you're not paying for answers. you're paying for Claude to re-read its own homework 30 times spent months blaming Anthropic for being greedy. turns out the problem was how I write prompts 5 minutes of reading basic plan now handles more than my old Max

Tried NotebookLM for my midterms this week; science and Spanish. The thing that makes it different from other AI study tools is that it only works from what you give it. Upload your notes and it builds study guides and practice questions from your specific class content. No random internet facts mixed in. Just your own material in a more usable format. As a student that's actually really useful. Most AI tools give you generic answers. This one knows your class.

@bryan_johnson Whoa 😮 We oftentimes get so enveloped in the digital world we forget to think of what we’re really made of. Sometimes I think it’s good to reflect and live in the present.

Guys, I’m an idiot. All this time I’ve spent trying not to die, I had toxic turf in my backyard. Artificial turf contains crumb rubber infill made from recycled tires, which leaches chemicals including PFAS, heavy metals, and polycyclic aromatic hydrocarbons. These compounds are linked to hormone disruption, carcinogenicity, and systemic inflammation. I don’t know how I missed it. It makes me question my basic competence in life. What gets me is that I try so hard to survey the world of potential idiocy. Then I find out there’s a monument to idiocy sitting right in front of my face that I was blind to. I’m removing the turf, yet I’m still stuck with this seemingly unsolvable problem of how to not be an idiot.

I've been doing a simpler version of this with my class notes and it changed how I study. Instead of rereading 40 pages before a test, I ask Claude to find connections between topics and surface what I've missed. It's not cheating, it's building actual understanding. The difference between using AI this way vs. copy-pasting an essay is huge. One makes you smarter, the other just looks like it.

LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So: Data ingest: I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them. IDE: I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides). Q&A: Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale. Output: Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base. Linting: I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into. Extra tools: I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries. Further explorations: As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows. TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

I've hit this exact thing building my iOS app in Swift, it's rough. The issue is context length. Feed Claude too much code at once and it starts losing the thread halfway through. By the time it reviews, it's basically reading it fresh. One function at a time. Painful to switch to but it works.

I'm not joking, I had Claude write a big batch of code last night. I am troubleshooting rn. I asked it to review, It said this is trash code and it needs completely reworked. We are spending credits to run in circles.

Today I learned how to give Claude long-term memory. You create a project folder with two files: INSTRUCTIONS.md (what the agent should do) and MEMORY.md (what it should remember about you). Every session, Claude reads them first. It knows your preferences, your voice, your past decisions. You don't have to re-explain yourself every time. I set this up for my content workflow today. Now my AI agent knows I'm 15, knows my brand, and knows how I like to write. That's not just a cool trick. That's actually a different way of working.

@OnlyTerp @claudeai It’s crazy that such a simple thing as usage limits is probably costing Anthropic thousands of users cancelling their subscriptions. Fix this now, Anthropic.

Canceling all my Claude subscriptions right now. Goodbye @claudeai thanks for alienating your users

@shiri_shh As a 15-year-old student I’m trying to learn all of the above. Between school, sports, and friends, it gets a bit challenging, but I always make time to learn about the skills that are going to create my future 🙌

generalists are about to win big If you understand a little of tech, business, and people, and can connect everything fast. you're sitting on a goldmine right now.

@DeryaTR_ It is kind of crazy how anthropic is trying to turn the blame onto users for utilizing its best model. Until this problem gets fixed, if it ever does, what is the best alternative to use for everything AI?

So Anthropic now claims there was no token-eating bug after all, it was all our fault for using Opus 4.6! Such dishonesty! I cancelled my Max account and, for the first time, turned negative toward an AI company. They claim to have the highest ethics & we need to trust them!? 👎

@mwfowlie In what ways is Codex superior? I know that regular Claude is far better than regular GPT, but I would appreciate some insight if Codex is truly better than Claude Code.

I don’t understand why people prefer Claude. I’ve been using both it and Codex everyday and Codex is far superior.