Mnimiy
@Mnilax • 7,663 subscribers
Writing & building in prediction markets and AI | HoC @xrocket_tg, ex. KOLs @blumcrypto
Shorts
Videos
Jenny Wen, head of design for Claude at Anthropic: "the design process is dead." what replaces it runs on machine-readable design systems In a 1-hour conversation, Jenny Wen breaks down why the discovery -> mock -> iterate loop is dying and what designers do instead. design system -> Claude Code -> every screen fixed at once, not one at a time i rebuilt the same 10-screen dashboard twice: ~6 hours of restyling by hand vs ~40 minutes when the fix lived in the system. how to build that system and hand it to Claude Code is in the article below.
Mnimiy177,647 Aufrufe • vor 4 Tagen
Boris Cherny, the creator of Claude Code at Anthropic, just listed 9 patterns that waste 73% of your tokens. in this podcast he breaks down exactly how the model burns tokens before it even reads your prompt: - the 14% you lose to CLAUDE.md before typing a word - the 13% you pay re-reading old chat history - the 11% from hooks you forgot you installed - why most "Claude got dumber" complaints are wrong if you're hitting Max limits more than once a week, you have at least 4 of these. Probably 7. instead of another show tonight, watch this. my own breakdown based on 400+ hours of usage is below, read it after the podcast
Mnimiy1,373,654 Aufrufe • vor 1 Monat
Anthropic's marketing-ops lead just shipped her entire weekly review in one slash command. live walkthrough. 8 connectors. one prompt that wakes up every friday. "this used to take me half a day" connect your sources -> save the prompt -> never write a weekly review again most people will copy the workflow. the line that decides whether you trust its output is one sentence inside the prompt.
Mnimiy222,646 Aufrufe • vor 26 Tagen
Claude Code Head invented a word for what most config files aren't doing: tokenmaxxing. 90% of it lives in one place: ~/.claude/settings.json. 125 keys in v2.1.105. official docs cover 40. 4 of mine aren't anywhere in the docs. i audited the whole file - 18 settings actually decide what your month costs. > enabledPlugins - mine had 14 on, 4 actually used. each idle plugin loads hooks and SKILL.md at session start. > mcpServers.enabled - false instead of delete. 9 unused servers cost ~30K tokens of schema every session. > cache_control breakpoint at the static/dynamic boundary moved my Opus month from $340 to $87. tokenmaxxing isn't a vibe. it's a file with 125 keys most people never open. watch this tonight instead of the new Rick and Morty drop.
Mnimiy82,796 Aufrufe • vor 22 Tagen
another trader went from -$18,000 to +$550,000 in a month after installing the right MCPs. think it's a joke? you can check him and see for yourself: $2,537.52 -> $18,189.73 (+616.83%) $4,660.97 -> $23,015.07 (+393.78%) $11,468.85 -> $36,842.38 (+221.24%) this is all on 5-min BTC markets on Polymarket. he’s not a financial analyst or a genius. after a streak of liquidations, he just deep-dived into the nuances of AI and figured out where his bot was losing to the rest. MCP plugins are the most underrated thing right now. you can do the exact same.
Mnimiy302,803 Aufrufe • vor 2 Monaten
trader connected Claude to Polymarket and made $390,000 in three weeks trading BTC 5-min weekly $151,843 daily $9,549 no magic. he just followed a guide: > installed poly-MCP and claude became his trading terminal > connected GPT Researcher - the bot finds patterns and events on its own > built automation with n8n and everything runs without him > taught claude to read the spread between Polymarket and Coinbase > launched Huginn, the terminal runs 24/7 > added Apprise - alerts go wherever he needs them result: while he was living his life, the bot made 19,000+ predictions with a 60% wr and brought in nearly $10k just yesterday his profile: just read the article, send it to your Claude and stop trading manually if you have questions, I'll answer everything don't waste your time.
Mnimiy230,653 Aufrufe • vor 2 Monaten
claude bot made $700,000 in a month for its owner. thanks to one file. > $42,921 today > $160,086 past week > $692,922 past month everyone writes claude motivational speeches: - "be a senior engineer" - "think step by step" - "be careful" doesn't work - claude already knows all that. what's missing is a CLAUDE.md like this guy's: ## Project high-frequency arbitrage on polymarket btc + eth 5-min and 15-min markets. dual-entry strategy. fixed risk, fixed profit target. ## Strategy: DUAL mode ## Mode A: high-confidence (60% of capital) - enter at 50-70c when poly_implied agrees with spot trend - target +50-100% per trade (~$6k profit) - size: $4,000-$8,000 per position ## Mode B: tail bets (40% of capital) - enter at 3-25c when own model says 35%+ probability - target +200-1300% per trade - size: $400-$1,800 per position ## IMPORTANT IMPORTANT: hold all positions to resolution. NO early exit IMPORTANT: skip if same market hit our books in last 60s IMPORTANT: cap daily risk at $50,000. hard stop ## Rules - NEVER exit before market resolution - NEVER trade on news (CPI, FOMC, ETF decisions) - NEVER size > 8% of bankroll on single position - skip first 60 sec of any 5-min market (illiquid) - pause 5 min after any $100+ BTC move ## Out of scope - never touch the wallet. read-only access - do not chase: skip if same market touched within 60s one rule = one mistake claude won't make again. each of his trades, around $6,000 profit. how? because that's what's written in CLAUDE.md: "target ~$6K per trade". not more, not less. > the system doesn't get nervous, doesn't chase, doesn't wait for a better price. > sees edge ≥ 4c and enters. > sees a tail 3c with own probability 35% - enters. > waits for resolution. > takes profit. > moves to next market. 29,596 times. his profile: this is the difference between "user of claude" and "operator of claude". the first writes wishes. the second writes technical specs. don't waste your time, level up your claude before it's too late.
Mnimiy88,024 Aufrufe • vor 1 Monat
IBM AI Engineer just listed the 7 skills you need to build AI agents in 2026. system design. tool contracts. RAG. reliability. security. evals. product thinking. all 7 are real. all 7 take months to learn properly. but here's the shortcut nobody tells you: most of these are already encoded in Claude Code skills you can install in 30 seconds. > superpowers does TDD + reliability for you > web-design-guidelines does eval + product thinking for you > valyu does retrieval engineering for you > simplify does code reliability for you the IBM video is what to learn if you want to build agents from scratch. my article is what to install if you want to ship agents tomorrow. both incredibly useful for different goals. watch the video. read the article. change how you work.
Mnimiy69,770 Aufrufe • vor 1 Monat
the bottleneck Karpathy keeps pointing at isn't the model. it's the file you wrote three months ago telling it how to work. his whole framing: code isn't the verb anymore. > you express your will to agents 16 hours a day. > running more of them in parallel is the unlock. > and he drops this line halfway through, no fanfare: "now you can have optimization over the instructions." that's the sentence. the instructions are the new bottleneck. and almost nobody has a process for optimizing them. i built one for myself. it reads 100 of my past Claude Code sessions and rewrites my CLAUDE.md from what the transcripts show, not from what i thought i wrote. one Saturday morning later: a 38-line memory file. 73% of my old CLAUDE.md got deleted. most of it was one-off corrections that hardened into permanent rules months ago and were quietly steering every agent i ran. four behavior patterns surfaced that i had never written down. the loudest one: my prose corrections outnumber code corrections 8.2 to 1. that ratio was running silently through every session for 90 days. you don't need a smarter model. you need an instruction file that still describes how you actually work. listen to the podcast for the framing. open the article for the script that does the optimization.
Mnimiy50,181 Aufrufe • vor 1 Monat
the guy who single-handedly raised Anthropic's engineering productivity by 70% just dropped a new podcast. Boris Cherny laid out the 9 core patterns he changed in his workflow to get there. the 3 most common traps: > bloated CLAUDE.md files that tax every single prompt before you've typed a word > re-reading old chat history on every message: by message 30 you're paying 30x the cost of message 1 > plugin hooks you installed 6 months ago and forgot, silently doubling your bill i'm confident 99% of you have hit at least one of these patterns and just shrugged it off. if you want to actually upgrade how you work with AI and Claude, watch this podcast to the end, then lock the knowledge in with my breakdown
Mnimiy57,760 Aufrufe • vor 1 Monat
Barry Zhang and Mahesh Murag from Anthropic (MCP creator) made it official: "Don't Build Agents. Build Skills Instead." so the marketplace did. it went from 16 official skills in October 2025 to 900,000+ community skills by May 2026. i tested 247 of them. kept 23. > Anthropic gave the mandate. the community shipped 56,250x supply > 90.7% deletion rate isn't a quality bug. it's what happens when "build skills" becomes everyone's homework > the 23 i kept all enforce one thing. Anthropic's actual point: skills as composable building blocks, not feature wrappers > the 224 i deleted all missed it, they wrapped features Claude already does, just packaged louder their talk explains why the format wins. my breakdown shows which 23 actually deliver on it. watch the talk. read the breakdown. install fewer skills.
Mnimiy37,934 Aufrufe • vor 1 Monat
$100,000 in 5 days: sports + claude + Kelly. - he created a Polymarket account on March 29 - deposited $4,300 - five days later had over $100k. no BTC. he just pointed his claude at a different category - sports. Kelly works everywhere. same: f* = (p − m) / (1 − m) he told Claude: "apply this to sports markets." > Cavaliers vs Lakers. Cleveland was priced at 2c: claude put in $1,075 and walked out with $18,460. > Spurs vs Clippers. market underpriced the Clippers. claude saw it and turned $38,050 into $81,752. +$43,702 on a single game. Tennis. NBA. MLB. LaLiga. doesn't matter. 5 days in this guy is already better than 98.52% of all Polymarket traders. his profile: everything you need is in the article below. send it to your claude. don't wait until tomorrow. tomorrow it'll be too late.
Mnimiy64,974 Aufrufe • vor 2 Monaten
you're running /compact every 10 minutes to fix a problem that disappears the second you give Claude one job instead of five. Anthropic shipped a clean 4-minute video on context management. /compact when the window fills up. /clear to reset. small files over big files. the practical tips work. the video covers the cleanup. it doesn't cover why your window keeps filling up in the first place, and the answer is usually that you're holding too many jobs in one prompt. look at what most people put in a single Claude call: > guess the right answer > choose between options > set the position size > watch the exit window > read the news for sentiment five tools' worth of state in one conversation. of course the window fills. i ran into this on a Polymarket bot: the prediction-layer version ate context constantly. /compact every 8-10 turns. i thought i needed better memory hygiene. i needed fewer jobs per call. i stripped the prompt down to one job: veto an entry i had already decided to take. the context window stopped filling. /compact went from every 8 turns to once a session, if ever. over 90 days that prompt blocked 128 trades. watch the 4 min, then ask why your window keeps needing it. clean context. lean prompt. nothing to compact.
Mnimiy20,635 Aufrufe • vor 28 Tagen
Pam Bondi is done. The AG is accused of protecting pedophiles and lying under oath. Jamie Raskin absolutely dismantled her in 5 minutes. Under Bondi's watch, the DOJ "accidentally" leaked Epstein victim names.. but scrubbed Donald Trump’s name from the docs. The Ted Lieu: "I believe you just lied under oath. And it’s all on video." Bondi: "Do not accuse me of a crime!" lol When asked why ZERO Epstein clients have been charged, Bondi launched into an incoherent rant about the stock market. Her stance? Americans should care about the economy, not a child trafficking ring. Pam was supposed to be a shield for the law, but she became a shield for the elites. Odds that Bondi leaves the Trump admin before 2027 just doubled. Is she next?
Mnimiy52,416 Aufrufe • vor 4 Monaten
Mark Pike just shipped a contract review in 9 minutes flat. live walkthrough. one slash command. by Associate General Counsel at Anthropic. structured Q&A instead of a linear walkthrough. drop the contract -> run the prompt -> ship the review before the call the one line that turns 90 minutes into 9 is one sentence inside the prompt. worth more than $2,000 of legal consulting.
Mnimiy13,772 Aufrufe • vor 25 Tagen
Anthropic's CPO just killed the boundaries between three Claude products. you should kill them inside your prompt too. Mike Krieger dropped a line most builders skipped: > "we're shipping our harness strategy, not a product." he doubled down later: the separation between the three products is "a broken abstraction we need to fix." Anthropic spent a year separating Claude AI, Cowork, and Claude Code into distinct surfaces. their own CPO now says the separation was the bug. they're collapsing it into one harness. the same abstraction is broken inside every Claude prompt you've written. you ask Claude to predict, pick, size, exit, and audit: five jobs glued together pretending to be one workflow. then you wonder why nothing comes out clean. i ran into this on a Polymarket bot. the prediction-layer version asked Claude to do everything. it lost money. then i stripped the prompt down to one job: veto an entry i had already decided to take. nothing else. no picking, no sizing, no exit logic. over 90 days the new prompt blocked 128 trades: 44 of them would have lost me $5,360. the bot's blocked trades saved more dollars than its approved trades earned. Krieger's lesson at the product layer is the same lesson at the prompt layer. - one harness. - one job. - fewer broken abstractions stitched together. Anthropic is collapsing their stack. you can collapse yours tonight. stop stitching five jobs into one Claude call.
Mnimiy10,196 Aufrufe • vor 1 Monat
Keine weiteren Inhalte verfügbar