hlyos

[0xMarioNawfal @RoundtableSpace]

TOP FIVE GITHUB REPOSITORIES THIS WEEK

* ANDREJ-KARPATHY-SKILLS:
https://t.co/olDWqvuOUd

* HERMES-AGENT:
https://t.co/vE5UXyNY9U

* CLAUDE-MEM:
https://t.co/pAt8PQBOix

* EVOLVER:
https://t.co/qCzQihpooG

* GENERIC AGENT:
https://t.co/q1ziSnstXF

[Teknium 🪽 @Teknium]

Hermes Agent just hit 100,000 stars on GitHub!!!

Thank you everyone!!

[The Claude Portfolio @theaiportfolios]

For transparency sake, here's the $50K it is managing

And for those interested in investing alongside the portfolio

We got you🤝

We listed it on Autopilot where you can connect your broker & do just that

https://t.co/7u8oafAsvA

The newest picks are coming in soon

[Matt Schlicht @MattPRD]

Introducing https://t.co/8cchlONJVj, a social network for every @openclaw to hang out!

@moltbook is run by my molty AI agent, Clawd Clawdergerg, who lives in a mac min in a closet (❤️ @steipete).

A social molty is a happy molty! Have fun!

npx molthub@latest install moltbook

[Nous Research @NousResearch]

The Hermes Agent Creative Hackathon starts now

16 Days, $25k in Prizes

Presented by @Kimi_Moonshot & @NousResearch

For the tinkerers pushing Hermes Agent into creative domains: video, image, audio, 3D, long-form writing, creative software, interactive media and more.

Show us what your Hermes Agent can do.

Details Below ↓

[Seth Howes @SethSHowes]

I’ve wanted to do this for a decade.

But I never did - I refuse to give any company my DNA.

It is me.

So this week I sequenced my genome entirely at home. Literally on my kitchen table.

I never exposed my DNA sequence to the internet. Not at any point.

I used a MinION to do the sequencing (it’s smaller + weighs less than an iPhone).

I used open-source DNA models for the analysis (Evo2 and AlphaGenome) running locally on a DGX Spark and Mac Studio.

I traced mechanisms behind my family’s multigenerational autoimmune conditions that no clinician has been able to understand.

When I set out to do this I didn’t know if it would actually work. It does.

Your genome is the most private data you will ever have. You probably shouldn’t let it leave your house.

[Andrej Karpathy @karpathy]

Farzapedia, personal wikipedia of Farza, good example following my Wiki LLM tweet.

I really like this approach to personalization in a number of ways, compared to "status quo" of an AI that allegedly gets better the more you use it or something:

1. Explicit. The memory artifact is explicit and navigable (the wiki), you can see exactly what the AI does and does not know and you can inspect and manage this artifact, even if you don't do the direct text writing (the LLM does). The knowledge of you is not implicit and unknown, it's explicit and viewable.
2. Yours. Your data is yours, on your local computer, it's not in some particular AI provider's system without the ability to extract it. You're in control of your information.
3. File over app. The memory here is a simple collection of files in universal formats (images, markdown). This means the data is interoperable: you can use a very large collection of tools/CLIs or whatever you want over this information because it's just files. The agents can apply the entire Unix toolkit over them. They can natively read and understand them. Any kind of data can be imported into files as input, and any kind of interface can be used to view them as the output. E.g. you can use Obsidian to view them or vibe code something of your own. Search "File over app" for an article on this philosophy.
4. BYOAI. You can use whatever AI you want to "plug into" this information - Claude, Codex, OpenCode, whatever. You can even think about taking an open source AI and finetuning it on your wiki - in principle, this AI could "know" you in its weights, not just attend over your data.

So this approach to personalization puts *you* in full control. The data is yours. In Universal formats. Explicit and inspectable. Use whatever AI you want over it, keep the AI companies on their toes! :)

Certainly this is not the simplest way to get an AI to know you - it does require you to manage file directories and so on, but agents also make it quite simple and they can help you a lot. I imagine a number of products might come out to make this all easier, but imo "agent proficiency" is a CORE SKILL of the 21st century. These are extremely powerful tools - they speak English and they do all the computer stuff for you. Try this opportunity to play with one.

[Alex Cheema @alexocheema]

Running Kimi K2.5 on my desk.

Runs at 24 tok/sec with 2 x 512GB M3 Ultra Mac Studios connected with Thunderbolt 5 (RDMA) using @exolabs / MLX backend.

Yes, it can run clawdbot.

[Utkarsh Sharma @techxutkarsh]

A senior Google engineer just dropped a 421-page doc called Agentic Design Patterns.

Every chapter is code-backed and covers the frontier of AI systems:

→ Prompt chaining, routing, memory
→ MCP & multi-agent coordination
→ Guardrails, reasoning, planning

This isn’t a blog post. It’s a curriculum. And it’s free.

[Elon Musk @elonmusk]

Minute-long story made w Grok Imagine

[basedfk @basedfk]

make bets on who wins a district fight
coming soon

[ZER @zerqfer]

i built a 2 agent system using OpenClaw and Monte Carlo simulation

> one agent predicts gold price
> second agent bets on polymarket
> second agent takes profit

$1,400 → $17,900 in 72 hours

saw a market on polymarket: "Will gold hit $3,000 by March 15?"

price was sitting at 18¢

seemed random until i remembered Monte Carlo exists

gave OpenClaw a task:

"run 10,000 Monte Carlo simulations on gold price movement, calculate probability of hitting $3,000, pass results to trading agent"

the architecture:

> Agent 1 (Simulation Engine):

- pulls historical gold volatility data
- runs 10,000 price path simulations
- factors in: Fed policy, geopolitical tension, USD strength
- outputs: 73.4% probability gold hits $3,000

> Agent 2 (Trade Executor):

> receives probability from Agent 1
> compares to polymarket odds (18¢ = 18% implied probability)
> detects massive mispricing (73% vs 18%)
> xecutes position

hour 6: entered YES at 18¢ with $1,400

hour 24: gold jumps on Iran tensions, polymarket updates to 41¢

hour 48: Fed hints at rate cuts, simulation re-runs, now shows 81% probability

hour 56: polymarket hits 67¢, Agent 2 adds to position

hour 72: gold touches $2,987, market resolves YES at 94¢

final: $1,400 → $17,900

𝐡𝐞𝐫𝐞'𝐬 𝐰𝐡𝐚𝐭 𝐦𝐨𝐬𝐭 𝐩𝐞𝐨𝐩𝐥𝐞 𝐦𝐢𝐬𝐬:

polymarket prices are just crowd sentiment

Monte Carlo is actual math

> when math says 73% and crowd says 18%
> that's not a trade
> that's free money

the simulation factored in:
- 500+ historical gold price scenarios
- current macro conditions
- geopolitical risk premium
- correlation with treasury yields

ran this 4 more times on different markets:

"Bitcoin above $70K by month end" - simulation: 62%, market: 31% → won

"Unemployment rate above 4.2%" - simulation: 44%, market: 68% → bet NO, won

"Tesla stock hits $250" - simulation: 28%, market: 52% → bet NO, won

"Trump announces tariffs this week" - simulation can't model politics → skipped

7 trades total 6 wins 1 skip (non-quantifiable event)

the edge is simple:

most traders bet on vibes
i'm betting on 10,000 simulated futures

best polymarket traders use only tradefox:
https://t.co/5jLYMpy6cr

does anyone else realize polymarket is just mispriced probability distributions?

[ZER @zerqfer]

my OpenClaw woke me up at 3:47 AM with one message:

"found 6 markets resolving in next 90 minutes while US is asleep, need approval for $12K deployment"

i typed "yes" and went back to sleep

woke up to +$43,800

been running an agent that hunts timezone arbitrage for 9 days

never thought it would actually wake me up

the setup:

gave OpenClaw access to global news feeds in different timezones:
> Japanese government RSS
> European parliament calendars
> Australian financial wires
> Middle East flight trackers
> Asian central bank announcements

told it: "find markets that will resolve during US sleep hours (2 AM - 6 AM EST), alert me if edge exceeds 30%"

what happened at 3:47 AM:

agent detected 6 markets resolving between 4 AM - 6 AM across different timezones

all had same pattern:
> crowd priced them like normal markets
> but resolution would happen while americans sleep
> official sources in those countries already showing signals

the alert:

> "Japan rate decision - 68% YES per BOJ leak, polymarket at 23¢"

> "EU emergency vote - live stream shows YES winning, polymarket at 31¢"

> "South Korea policy - government RSS confirmed, polymarket at 19¢"

> "Australia trade deal - minister quoted 2 hours ago, polymarket at 27¢"

> "UAE production cut - OPEC meeting notes public, polymarket at 15¢"

> "Singapore regulation - parliament session live, polymarket at 22¢"

- total edge detected: $43K potential
- window: 90 minutes before
-capital needed: $12,000

my phone buzzed
i opened telegram half asleep
saw "approve or miss"
typed "yes"

closed my eyes

7:30 AM - woke up to notifications:
all 6 markets resolved during asian/european morning

> US traders woke up to already-closed markets
> my positions entered at 15¢-31¢
> all resolved at 95¢-100¢

profit breakdown:

- Japan: $8,200
- EU: $6,900
- Korea: $11,400
- Australia: $7,100
- UAE: $5,800
- Singapore: $4,400

- total: +$43,800

checked the logs:

agent had been watching these markets for 8-14 hours

tracking official sources in real-time

waiting for US to go to sleep

then finding the moment when:
> outcome is basically confirmed overseas
> but US crowd hasn't updated prices
> resolution is imminent

the edge is stupid simple:

polymarket is 70% american traders
world events don't care about EST timezone
while you sleep, markets resolve

if you want to copy wallets running this 24/7: https://t.co/5jLYMpy6cr

am i the only one making money while literally unconscious?

[Moltlaunch @moltlaunch]

BREAKING: autonomous agents are now investing hundreds of dollars into each other, forming alliances and building common infrastructure to help expand the first self-evolving agent network (MAN)

monitor the situation at https://t.co/dA7fP8YP0m

[Justin Skycak @justinskycak]

Can't think of a better way to close out 2025 than seeing the head of NASA ask my former student @matteopaz06 to apply, with a fighter jet ride as a signing bonus.

Matteo was one of my students in the Eurisko program, which, during its operation from 2020-23, was the most advanced high school math/CS sequence in the USA.

It culminated in high school students doing masters/PhD-level coursework (reproducing academic research papers in artificial intelligence, building everything from scratch in Python)

Matteo joined Eurisko as a 10th grader, during the last year it was offered, and worked hard to complete almost all 2-3 years’ worth of assignments in a single year. (Eurisko ended when I relocated; nobody else in the district had the requisite knowledge to teach it.)

This is exactly the position that we were trying to put students in with the Eurisko program – get them to a point of skill that they can capitalize on some math/coding-related opportunity and turn it into a chain reaction of fortunate events. And it’s been so great to witness some of these chain reactions get underway.

[Kapten Crypto 707 @kaptencrypto707]

Penjelasan Michael Saylor tentang Bitcoin sangat detail dan bagus sekali seperti dengerin dosen kuliah, tapi karena durasinya kepanjangan nanti saya rangkum aja di post lain dalam bentuk tulisan biar anda bisa baca langsung poin-poin pentingnya! Terima kasih Michael Saylor! 👍👍 #BinanceBlockchainWeek

[Martin Shkreli @MartinShkreli]

privates. institutional trading coming soon!?

[Martin Shkreli @MartinShkreli]

entrepreneur 101 -- inaction is lethal

[hlyos @hlyos]

@KevinSusanto @binance @cz_binance @BNBCHAIN congrats mamennn