Roan

@0xRicker always great to hear andrej

Andrej Karpathy just reveales how LLMs actually thinks: "GPT-4 knows it failed. It just won't tell you unless you ask." >80% of GPT-4 errors are recoverable - the model already knows it screwed up. It has 80 transformer layers and spends the SAME compute on every single token as your brain In a 20-minute speach at Microsoft Build, Karpathy reveals the full psychology of LLMs. Worth more than any $500 prompting course you've seen on your timeline.

My friend applied to 200 tech jobs in two years. No MIT. No Stanford. Last month Anthropic offered him $750,000. I asked him how he broke in from zero. He sent me the exact video that got him in. A 4-hour course on mastering Claude Code. I watched it last night. Halfway through, I realized I've been using Claude Code completely wrong for a year. Bookmark this and read the article below. • 00:00 - Claude Code setup • 49:34 - building apps with Claude Code • 2:07:52 - prompting Claude Code • 2:46:16 - Claude Code for production

@RitOnchain always good to hear about AI from quants

Senior Quant Researchers just revealed how they use Generative AI for trading and asset management. 60-minutes. free. By Quant PHD Researchers. here's what they cover: • why LLMs hallucinate financial logic (like misapplying the square root of 252) • agentic AI frameworks for parsing alternative data (10-Ks, Fed speeches) • evaluating synthetic data via "train on synthetic, test on real" protocols • the myth of explainability vs 7-billion parameter trading models worth more than any $900 Quant course.

@Bober_smart interesting share bober, thank you for alpha

@nofadsec good visualisation

I don't ask AI to predict the market. I ask it to prove me wrong. Again. And again. Every new prompt is another attempt to break my thesis. "What am I missing?" "What's the strongest case for NO?" "What news could completely flip this market?" I don't stop when AI agrees with me. I stop when it can't make a stronger case against my thesis. That's when I finally have enough confidence to open a position. This article made me realize I've been using AI the wrong way.

@0xSlyth sounds insane bro

A 19 YEAR OLD BUILT A QUANT TRADING WEBSITE THAT THINKS LIKE A HEDGE FUND most traders stare at charts he built a system that watches the market for him Here's what it does: -> Tracks real time market data across multiple assets -> Identifies high probability trading setups automatically -> Analyzes order flow and market structure -> Backtests strategies before execution -> Generates quant based trading insights in seconds -> Visualizes complex data through a beautiful UI the crazy part? he didn't build another TradingView clone he built a quant trading machine while everyone else is looking for the next 100x trade His system is: -> Calculating probabilities -> Finding statistical edges -> Filtering bad setups -> Monitoring the market 24/7 -> Preparing the next opportunity before it appears on your timeline the edge isn't predicting the future it is building systems that understand the present better than humans can the next generation of traders won't spend all day watching charts they will spend their time building systems that never stop watching them Bookmark this before quant trading becomes everyone's unfair advantage

@RuujSs This lecture on building allocations + your article on building quant portfolio - dangerous alpha today

Met a quant making mid-seven figures running systematic allocation at a quant fund. I asked him how he learned to build allocations that don't fall apart the moment market correlation shifts. He sent me the exact video that got him in. MIT's 79-minute portfolio management lecture. You won't find anything better about the actual math of diversification, risk parity, and why your weights swing wildly when you feed new data into a raw covariance matrix than this video. I watched it last night. Halfway through, I realized I had been running optimizers on raw sample covariance matrices for years and wondering why my allocations destabilized every time the window changed. Bookmark this and watch today. Then read the article below. • 00:00 - portfolio construction roadmap: sizing, objectives, and constraints • 30:23 - two-asset variance and correlation math • 35:34 - risk parity and why textbook MPT breaks • 40:20 - rebalancing discipline and why weight drift destroys your allocation

@ArchiveExplorer damn bro, thanks for saving my money

Someone built a free open-source version of vercel v0. no $149/mo subscription needed. it's called screenshot-to-code. solo project by abi raja, sitting at 73,276 stars. drop in any screenshot, mockup or screen recording and it ships working code: - outputs html+tailwind, react, vue, bootstrap or ionic - video mode turns a screen recording into a live prototype - pulls real logos and images out of your screenshot via gemini - works with gemini 3.1 pro, claude opus 4.8, gpt-5.5 - self-host via one-line docker compose 100% free. open source.

@polysuccubus @Polymarket thanks for motivation bro haha

Yesterday he was down -$665. Today one $19 combo changed everything. How he turns 19$ into +$20,616 PROFIT!!! This is probably one of the craziest Polymarket stories I've seen. Yesterday, ItsShiven was sitting at -$665 all-time PnL. Today he built a simple 2-pick combo on tennis. He risked just $19.06. The result? +$616 profit +3,233% ROI Finished #1 on the Combo Leaderboard And unlocked a $20,000 bonus from Polymarket From a losing account to +$20,000 life-changing day in just a few hours. Do you think you could repeat what this guy just did? Or was this a once-in-a-lifetime run?

@Dipper_pol nice share

Andrej Karpathy builds GPT from scratch in one 2-hour video - before he led pretraining at Anthropic: he starts with an empty file and tiny Shakespeare, and ends generating infinite fake Shakespeare, character by character - the exact same way ChatGPT runs, just token by token. "now we get to the crux of self-attention - this is probably the most important part of this video." then he explains the whole engine: every token emits a query (what am I looking for) and a key (what do I contain), and attention is just them finding each other. by the end he connects it to the real thing: "to train ChatGPT there are roughly two stages: pre-training, then fine-tuning." this one video is the clearest path from "I use ChatGPT" to "I understand how it's built." Watch it today ↓

@0xClodex legendary talk from andrew ng, bookmarked this

Andrew Ng codes with Claude Code, OpenAI Codex, Gemini CLI - and now from his phone. his stack in 2026, and why the "job apocalypse" isn't real: "six months ago I was almost all Claude Code. these days still a lot of Claude Code, but increasingly OpenAI Codex, with a mix of Gemini CLI and opencode." in a LangChain fireside, the DeepLearning.AI founder on why the frontier of coding agents shifts every few months - and he now even codes from his phone. his bigger call: forget the "job apocalypse." "the doomsaying got more traction than I'd have guessed - including the job apocalypse, which I don't think is going to be a thing." the real shift isn't job loss - it's that when software gets 100x faster, everything else becomes the bottleneck: product, marketing, legal, design. Watch it today ↓

@gippp69 wow bro, this repo looks game changer - saved it.

SOMEONE GAVE CLAUDE FABLE 5 A CONTRACT, A $5 DAILY BUDGET, AND A MANAGER. THIS F**KING DANGEROUS SYSTEM CAN CLEAR A WEEK OF BACKLOG WHILE YOU SLEEP. 00:03 he opens Microsoft’s 4,900 star Agent Governance Toolkit, built for policy enforcement, isolated execution, identity controls, and protection against all 10 OWASP agentic risks. setup starts with 3 files. CONTRACT MD sets the limits, boundaries MD defines what the agent can touch, and signoff SH runs every test before anything ships. four roles split the shift. one model reads the logs, Fable picks the highest value task, another writes the code, and a fresh Fable reviews the final diff. a $5 cap stops runaway sessions, commits above 150 lines need approval, and autonomy unlocks only after 20 runs at a 95% pass rate. one failed run sends the agent back to probation. the repo adds the guardrails, but the contract is what turns Claude from a chatbot into an employee.

@thejayden this is very thoughtful jay, thanks for sharing

THIS is the MOST IMPORTANT article you’ll read TODAY.

@RuujSs solid break down on building quant portfolio, thanks ruuj for this masterpiece

@eng_khairallah1 this is gold session for prompting, thanks for sharing

@Av1dlive wow bro, i will setup it today and see how it goes

@Av1dlive this article is banger, avid

@RitOnchain using patchTST like jane street would be game changer

@0xkvro ofc they are the creator of claude code haha

@RohOnChain anthropic knows claude best

Met a guy making $1.2 million a year as a prompt engineer. I asked him how he learned prompting so well. He sent me the exact video that that got him in. Anthropic's 2 hour prompting course. You won't find anything better about prompting Claude than this video. I watched it last night. Halfway through, I realized I have been prompting Claude completely wrong for years. Bookmark this and read the article below. • 00:00 - the prompting playbook • 33:30 - prompting class 1 • 1:01:16 - prompting class 2 • 1:26:10 - prompting class 3