Angehefteter Tweet
Codez
316 posts
Codez
@0xCodez
Content creator | AI researcher & builder | AI insights from 2030 | @zscdao
San Francisco Beigetreten Mayıs 2026
98 Folgt4K Follower
Head of Claude Code just mass he has hundreds of agents running 24/7
scanning X, GitHub, and Slack to decide what to build next
he doesn't write code. he doesn't even prompt Claude anymore
"I have loops that prompt Claude for me. my job is to write loops"
in November he uninstalled his IDE. hadn't opened it in a month
his advice to every founder in the room: "underfund everything. if it needs 4 engineers - put 2 and give them tokens"
30 minutes. free. on Acquired
bookmark & watch ↓
Codez@0xCodez
English
@0xCodez Creating loops that create loops. Someone still has to reason about what the loops are for. That someone is not the model.
English
Codez retweetet
Creator of Claude Code :
"I don't prompt Claude anymore. I create loops - and the loops do the work. My job is to create loops."
In 30 minutes, Boris breaks down his real daily Claude Code setup.
Claude + loops + routines + dynamic workflow
Worth more than a $500 vibe-coding course
Codez@0xCodez
English
@0xCodez 😅 Some thoughts
x.com/heycqing/statu…
Blep-Cat(海青)@heycqing
The 14-step automation stack is real. Set it up. But step 10 will quietly destroy you if you skip this part: "A routine runs autonomously with no follow-up questions. Anything ambiguous becomes a coin flip on every run." That's buried in the doc. Here's what it actually means: Most people's prompts look like this: "Every morning, check GitHub issues and summarize them." A Routine running that at 7am will give you something different every single day. Sometimes a Slack message. Sometimes a draft PR. Sometimes nothing. The prompts that actually work define 4 things: - What to look at (exact repos, exact labels, exact timeframe) - What "done" looks like (output format, where it goes) - What to do when something's missing (fail loudly or skip quietly) - What NOT to do (the deny list matters as much as the allow list) The automation stack is a force multiplier. A vague prompt × automation = vague results at scale. A precise prompt × automation = leverage. Fix the prompt first. Then set the cron.
English
@0xCodez This is the kind of AI content people can actually use.
English
26-YEAR-OLD GIRL QUIT HER JOB AND BUILT A SMALL SOCIAL NETWORK FOR NYC CAFES. 31,000 USERS IN 4 MONTHS. NOW IT MAKES $18,400/MO FROM LOCAL SHOPS
she didn’t try to build another instagram. she built a tiny app for one obsessed niche: people who save cafes, share lists, follow local taste, and discover places before they go viral on tiktok
the product is simple. profiles, posts, likes, saved lists, search, comments, and a feed. that is basically every social network at the core. the hard part was never the idea. it was needing 5 engineers to make it work
claude code changes that. one person can now build auth, database, feed logic, profiles, follow system, storage, notifications, and deployment with supabase and vercel instead of hiring a full team
the money is not from ads. cafes pay $199/month to claim their page, boost new menu drops, see which lists saved them, and post local offers. power users pay $8/month for private maps and early city guides
most people still think social networks need millions of users. she proved the opposite. 10,000 people in one niche can be worth more than 100,000 random users scrolling for nothing
small social networks are the new local media businesses. claude code just made them cheap enough for one person to start one from a laptop
Shadow Nick@doublenickk
English
Fortnite pros when they realize AI replaced them:
> while pros scrimmed, AI leveled up
> AI agents trained on thousands of matches
> claude analyzes replays and writes Verse logic
> each new version plays smarter than the last
> epic pays creators whose bots drive engagement
> the human-AI gap in esports is closing fast
> by 2027 winning teams may not be fully human
wast3@0xWast3
AI-trained Fortnite bots are coming for esports titles and the people building them are already getting paid while pro players were grinding scrims a few creators were teaching machines to outplay them what's changing: > Claude analyzes match data, writes Verse agent logic > bots learn decision patterns from thousands of games > each iteration plays smarter than the last > Epic pays creators whose agents drive engagement the gap between human and AI in esports is closing fast the teams that win in 2027 might not be fully human and the developers training those agents right now are collecting checks from a $350M pool while they build bookmarked and learn
English
@ArchiveExplorer Top-tier watch, btw, are you using Obsidian for your daily routines, bro?
English
This guy cancelled three subscriptions and deleted two apps
his research output got better after
for two years he ran five tools in parallel. Notion. Readwise. X bookmarks. Browser bookmarks. ChatGPT
five places to look for the same piece of information
he called it a research stack. It was actually five locked rooms with no master key
four months ago he shut all of it down and rebuilt everything inside one Obsidian vault with Claude as the intelligence layer
every Sunday night Claude reads the full week. Highlights, links, ideas, notes. Everything that came in
Monday morning a synthesis is waiting on his screen
connections between notes written weeks apart that he had completely forgotten were related
those connections are now the source material for most of what he publishes
he built the whole thing in one weekend
most people keep adding tools when the output disappoints them
he removed four and the output improved
the problem was never the tools
every extra tool was just more work only he could do
Dami-Defi@DamiDefi
English
@insomnia_vip @Polymarket Damn, this trader looks interesting. Thanks for the share, bro - bookmarking it!
English
For 10 years he managed air traffic without losing a single plane
Then the tower was automated and he lost the job
A few months later he turned $1,100 into more than $800,000 on @Polymarket
His wallet is public: @easyclap?via=insomnia" target="_blank" rel="nofollow noopener">polymarket.com/@easyclap?via=…
Most traders are still looking for the perfect signal
He built a system that runs hundreds of them at once
At the center is Claude Opus 4.8
Around it are up to 250 AI agents scanning order books, market data, news feeds and prediction markets in parallel
Every opportunity gets broken down, checked, scored and reviewed before capital is deployed
In one trade, a Bitcoin market was trading at just 0.3c
The system accumulated 27,684 shares for $62.44
A few days later the position settled for $15,127
That's a 25,312% return from a market most traders never even noticed
He doesn't really operate a trading bot
He operates an entire trading desk made of AI agents
The tower got automated
Then he automated everything else
Connect wallet to this bot and automatically copy every trade: t.me/poly_parlay_bo…
kiosa@thegreatest_sv
English
Nobody is talking about what this Nvidia laptop actually means for creators
Jensen Huang walked on stage and held up the RTX Spark like it was nothing special.
Full Blackwell GPU. 1 petaflop of AI performance inside a laptop.
It renders, edits and runs local AI models faster than most desktop setups people have at home.
You pay zero monthly fees because everything runs locally on the device.
Creators who switch stop paying $300 a month in tools immediately.
Video editors are already charging $150 an hour using the AI workflows this chip makes possible.
At 8 hours a day that is $3,600 a week from a single laptop.
Most people are still waiting 3 hours for a render this thing finishes in 10 minutes.
The reaction in this clip says everything.
Follow if you want to know what actually matters before everyone else figures it out.
winkle.@w1nklerr
English