F**k

[F**k @Jomininini]

@YYDSGZH888 老牛吃嫩草 猪拱白菜 癞蛤蟆吃天鹅 第四个是啥

[VALIX @RetroValix]

This guy built a two-sided trading bot on Polymarket and made $233,695

His algorithm trades short-term crypto Up/Down markets using asynchronous complete-set accumulation and dynamic inventory management:

1. Starts building inventory almost as soon as the market opens

Its first purchase occurs a median of 33 seconds after the market opens

It keeps buying through most of the trading window. In 5 minute markets, its last purchase occurs a median of 223 seconds after opening

2. Adds the opposite outcome to its position

It bought both Up and Down in 88.76% of markets

It starts buying the opposite side a median of 35 seconds after its first purchase. It then keeps switching between outcomes as the market reprices

3. Turns most of its inventory into complete sets

89.82% of the shares it buys can be matched into Up + Down pairs

The average combined cost of a pair is 96.35c, giving it an edge of 3.65c

But this is not pure arbitrage

Only 58.66% of two-sided markets ended up with an average combined Up + Down cost below $1. The remaining 10.18% of shares are unpaired, leaving a directional residual

Its Polymarket account: norm1e69

You can build your own trading bot here:
https://t.co/JVofcJa07i

(A trial is available after signing up)

The algorithm’s main edge comes from asynchronous pairing: it keeps switching between Up and Down, matches most of its inventory into complete sets, and retains directional exposure through the unpaired remainder

[kiosa @thegreatest_sv]

whoever leaked this is f*cking crazy

someone mapped 300+ AI agents into one GitHub repo - and basically leaked the shortlist of what's actually worth trying.

coding agents. browser agents. memory. research. multi-agent teams. sandboxes.

all sitting on one page.

but everyone opens it and installs the same five names. the interesting stuff is what nobody reposts.

want an AI that hacks your own app before someone else does?

-> Strix
https://t.co/gi7kWVX4I0

want a thousand agents arguing about what happens next, so you get a forecast instead of a guess?

-> MiroFish
https://t.co/qESbV4WUFu

want your agent to know everything you did on your computer this week?

-> screenpipe
https://t.co/pKyPy99ulo

want memory that understands how facts connect, not a pile of old chats?

-> Graphiti
https://t.co/GgepxkkJgc

want an agent clicking through a whole desktop that isn't your laptop?

-> Cua
https://t.co/O6XuEKyXcv

and that's barely scratching it.

~225k stars across five repos most people have never opened.

the real cheat code isn't downloading all of them.

it's opening the repo before you build anything and asking:

"has someone already solved this?"

because there's a pretty good chance the answer is yes - and the open-source version already has thousands of people testing it for you.

I went through the map and pulled out the agents I'd actually start with.

full AI agent list below

[marfin @marfinxx]

this is pure f*cking treasure

A Stanford AI research group found how to orchestrate Claude Opus 5.5 and GPT-6.1 Sol together, and it completely breaks the search scaffolding wall

most developers try to combine frontier models by chaining prompts in one context window or hardcoding rigid evolutionary loops. you burn tokens on context bloat and freeze models into fixed search rules that out-date themselves within 5 iterations

Stanford's architecture eliminates human-designed search scaffolding and splits the cognitive stack:

> search director: Claude Opus 5.5 plans the search, querying a persistent idea-graph where MAP-Elites and MCTS reduce to single Cypher queries
> candidate proposer: GPT-6.1 Sol explores high-entropy code variations inside isolated execution sandboxes
> zero context bleeding: sessions reset after each iteration to prevent prompt bloat while the graph stores lineage
> evaluator isolation: candidate code never touches the scoring process, stopping reward hacking and test leakage cold
> meta-agent distillation: an offline meta-pass extracts verified lessons and updates search guidance across branches

the benchmark metrics outclass standard discovery baselines:

> 3.2x lower model spend than fixed evolutionary frameworks
> 1st place rank across 7 competitive AtCoder heuristic contests against human competitors
> beats published SOTA on Anthropic kernel builder and 11 mathematical optimization tasks
> 0% reward hacks: candidate-controlled metric tampering eliminated

Opus directs the search graph. Sol explores the code

you stop writing rigid search harnesses. you let frontier models own the discovery loop

[kiosa @thegreatest_sv]

this is the list nobody wants you to bookmark.

10 GitHub projects where AI agents actually make you money

not another framework zoo. client work, content, leads, voice, trading.

-> n8n · AI workflow automation you sell to clients on retainer. the agency backbone
-> https://t.co/BBZfRhkSaO

-> Dify · ship chatbots, RAG apps and agent workflows for businesses without a dev team
-> https://t.co/yzg8eMkSol

-> Firecrawl · any website -> clean structured data. scraping gigs, lead lists, datasets
-> https://t.co/vnKNOKPbS2

-> browser-use · agents that click through the browser for you. sell the automation, not the hours
-> https://t.co/aff20DFcJu

-> TradingAgents · multi-agent trading firm in a repo: analysts, researchers, risk desk (research only - not an atm)
-> https://t.co/wGJ1ROMRvm

-> screenshot-to-code · screenshot -> clean HTML / Tailwind / React. landing pages in minutes
-> https://t.co/neD3z2puLK

-> Marketing Skills · CRO, copywriting, SEO and growth skills for Claude Code. a marketing team in a folder
-> https://t.co/9FV6U8NWpw

-> Postiz · agentic social media scheduler. run 10 client accounts from one dashboard
-> https://t.co/D8uKTJfiRV

-> VideoLingo · subtitles, translation and dubbing in one click. sell localization to creators
-> https://t.co/TTQJ79T68v

-> Pipecat · realtime voice agents. AI receptionists and phone bots local businesses pay monthly for
-> https://t.co/32JxqNQ1VO

~985k stars of "agents that touch revenue"

save this. pick one. charge someone for the output.

[F**k @Jomininini]

睡不着，想到一个问题，婴幼时在我们还没认识文字，看到满大街的文字是什么感觉？ 我怎么一点都记不得了

[F**k @Jomininini]

@yw9715 少他妈风凉话，连发声的勇气和意愿都没有

[F**k @Jomininini]

@JDVanceNewsX I don not believe this is a proper way to judge a guy who defends his home. The war should be stopped but not based on the surrender of the defenders

[F**k @Jomininini]

@911PPD @meirdasai8881 @GetVidoBot

[F**k @Jomininini]

@KPKP996 @meirdasai8881 @GetVidoBot

[F**k @Jomininini]

@KPKP996 @meirdasai8881 @DowloaderBot

[F**k @Jomininini]

One swimming pool a day

[F**k @Jomininini]

Slow down @ Krabi Thailand

[F**k @Jomininini]

@imkinkybeth Hi Same here

[F**k @Jomininini]

@lao_jiang50163 Brilliant

[F**k @Jomininini]

@atemptlust 香港呢

[F**k @Jomininini]

@BrianRoemmele Anyone can tell me how this data visualisation is made, what tools to use?

[F**k @Jomininini]

@celineyan486992 哪里的？

[F**k @Jomininini]

@Pathos_7 所以你到底是在哪里