Aditya Lesmana

Mostly harmless. Building startup one brick at a time. Nice to meet you. 🇮🇩🇸🇬🇺🇸

[ℏεsam @Hesamation]

https://t.co/VnC5pfDaUA

[Movez @0xMovez]

Andrej Karpathy predicted the future of AI once again:

“Everyone’s renting frontier models for jobs a local 3B model could do. Small Local LLM's are the future.”

this 18-page PDF breaks down Karpathy's case for running that core on your own machine.

the real question isn't "is the local model as smart?"

It's "which of my 1000 calls ever needed the smart one?"

[Anatoli Kopadze @AnatoliKopadze]

Andrew Ng just dropped the best 2-hour course on Graph Engineering, from single agent to full automation:

9:14 - building your first agent
33:11 - how loops really work
1:02:46 - from loops to graphs
1:30:15 - agents that fix their own code
1:49:05 - the system that runs itself

these two hours make every agent tutorial you saved this year useless

Prompts → Agents → Loops → Graphs

most people stop at one agent and think they've automated something

the real part is the last forty minutes, where the system keeps running without him

watch it today

then go further with my step-by-step guide on loops and graphs below

[Aditya Lesmana @adityalesmana]

https://t.co/GvIDEvCSI7

Singapore is on another level already

[beamnxw ./ @beamnxw]

this is pure f*cking treasure

20 useful GitHub projects for a system that captures sources, connects ideas, remembers context, and helps agents act on it

your second brain should get sharper after every session

CAPTURE THE INPUT
01 Chubby Skills
▸ https://t.co/InxyRwMZtz
02 OpenWiki
▸ https://t.co/bLeUouBLuu
03 Agent Second Brain
▸ https://t.co/WANfN9tVP4
04 DocMason
▸ https://t.co/rQsMrIDGh0
05 DocsAgent
▸ https://t.co/R8DF9NI0tt

CONNECT THE IDEAS
06 claude-obsidian
▸ https://t.co/uhwe1f5n6X
07 SwarmVault
▸ https://t.co/QNxk0QvLYH
08 sage-wiki
▸ https://t.co/OQIkSucHAA
09 Vault Curate
▸ https://t.co/FeR1r3vLle
10 COG Second Brain
▸ https://t.co/1gtpmSyJuy

REMEMBER WHAT MATTERS
11 Hindsight
▸ https://t.co/3cXNIFAyDN
12 memU
▸ https://t.co/iCoOwoBIT3
13 TencentDB Agent Memory
▸ https://t.co/i2DaJnwGhu
14 agentmemory
▸ https://t.co/3OlbQk5CPq
15 OpenViking
▸ https://t.co/Ydr8K54XxW

PUT IT TO WORK
16 Open Second Brain
▸ https://t.co/DiOBxmK4Gh
17 Second Brain Cloudflare
▸ https://t.co/WlokLe12JV
18 makerskills
▸ https://t.co/Q1RQFhStsL
19 Row-Bot
▸ https://t.co/I1KBQwA7hk
20 MateClaw
▸ https://t.co/N9vGfry4no

the loop:

capture the source → turn it into linked, checkable knowledge → recall the right context → act with it → write the correction back

3 builds I'd explore:

creator: Chubby Skills → SwarmVault → Hindsight → makerskills
researcher: DocsAgent → sage-wiki → memU → Row-Bot
team: DocMason → COG Second Brain → TencentDB Agent Memory → MateClaw

save this, then build a second brain for your business ⭣

[Yarchi @undefinedKi]

My second brain article passed 8 million views. So I put the whole setup, the tools, the learning material and everything around it in one place. Free

A repo and a site. What is in there:

> 109 pages on the site
> The guide: 10 sections and 65 pages, concept through troubleshooting
> 5 tracks on top of it, 44 pages, 15 of them build guides with code that runs
> 18 agent skills, 72 slash commands, 6 subagents
> 5 Python scripts: graph export, link checker, vault stats, chat converter, site builder
> A starter vault template with its own CLAUDE.md
> 87 resources: 28 tools, 26 Obsidian plugins, 15 repos, 12 skills, papers and articles

There is also a track for each of these:

> Knowledge graphs
> Jev engineering
> Agent harnesses
> Loop engineering
> Eval engineering

The Second Brain guide is a good starting point, and I'd recommend that beginners start there.

If you're a more advanced LLM user, move on to the additional resources. I'm sure you'll find a lot of useful information there.

The website and repository are constantly updated. New tooling shows up every week in this space.

Repo: https://t.co/GpYVL1Ogh5
Website: https://t.co/8dSeufUJAJ

[Aditya Lesmana @adityalesmana]

@jack_9947 Cycle

[Aditya Lesmana @adityalesmana]

🥳 https://t.co/ta8RqziwUT

[Hahnbee Lee @hahnbeelee]

https://t.co/2auGCURfEe

[Scient @scientxbt]

this is insane. i genuinely don't understand why ambitious people aren't shown this lecture before their careers start consuming their entire lives.

clayton christensen spent his career studying why successful companies collapse. in his final class, he asked students to apply the theory to themselves: if you keep allocating your time the same way, what life are you actually building?

he had already seen the answer in his own harvard mba class. everyone looked successful at the fifth reunion; by the 10th, 15th, 20th, and 25th, many were unhappy, divorced, and living far from their children.

work shows you the score immediately. close a sale, ship a product, finish a presentation, earn a promotion, get paid.

an hour with your child may produce nothing you can measure today; it may take 20 years to understand what that hour built. so the next free hour goes back to work, one rational decision at a time.

this is how people build lives they never planned: through hundreds of right decisions that lead in the wrong direction, day after day.

money, titles, and headcount are easy to count. christensen believed a life should be measured by the people who became better because you were there.

he died in 2020.

one question remains: if someone saw only where your time, energy, and attention went this year, what would they think actually mattered to you?

the full 19-minute lecture is in the video below.

[Aditya Lesmana @adityalesmana]

@felixprehn Report

[CyrilXBT @cyrilXBT]

POV: you bought a "local AI setup" course, then found a single developer's free GitHub repo running a 2.8 trillion parameter model off your own SSD with zero subscription.

[Arief @coelacanthuss]

Ini adalah satu buku penting buat yang mau tau ikan pasar di Indonesia tapi ga tau namanya. Buku ini berisi deskripsi, foto, dan nama ikan dalam bahasa Indonesia serta Inggris. Gila ini bagus banget woi. Bukunya bisa diunduh gratis juga.

https://t.co/qfR5y4BTIC

[Sprytix @Sprytixl]

https://t.co/vMbIVOfkoR

[J.B. @VibeMarketer_]

https://t.co/l62nWZhBmO

[Aditya Lesmana @adityalesmana]

@aerorun

[Ibrahim Arief @ibamarief]

magnet:?xt=urn:btih:13ffbf49431b19b85fdee41beb565ed5beb611aa&dn=d6993ad34309.tar.zst.age

sha256 40c686202840b8af0325fcac54e2eb43f4f5a736bd9818cbbea78ce1226a5d7f

encrypted archive, please help safeguard, decryption key to be published

[Jack @jackcoder0]

A guy paid $20/month for ChatGPT Plus.

He used it for writing emails, brainstorming, answering questions, and summarizing documents. The same way he's used it since 2023. The same prompts. The same text-in, text-out workflow. The same chatbot.

On September 3, 2026, OpenAI released GPT-6 Astra. He saw the new model option in ChatGPT. He assumed it was another incremental upgrade slightly smarter, slightly faster, same chatbot.

His friend a product manager who'd been testing Astra since the preview stopped him from typing his usual "write me 5 subject lines" prompt.

"You're about to use GPT-6 the way you used GPT-4. That's like buying a Tesla and using it as a shelf. Astra doesn't just answer questions. It uses your computer. It opens browsers. It clicks buttons. It fills forms. It navigates websites. It builds and hosts live websites from a single sentence. It writes code and runs it. It keeps notes across sessions so it never forgets what it learned about your project. Your $20/month chatbot just became a digital employee."

He told him GPT-5.6 was the smartest assistant in the room. GPT-6 Astra is the assistant that leaves the room, walks to the computer, and does the work. The gap isn't intelligence. It's agency. The model went from generating text to completing tasks multi-step, across applications, without the user copying, pasting, or switching tabs.

Here's every GPT-6 Astra capability most ChatGPT users won't discover on their own 🧵

[DAN KOE @thedankoe]

https://t.co/klNSdaI7aa

[rvaniaaa @rvaniaaaa]

a researcher told me why he abandoned his second brain after six months. “the more i added, the more i had to maintain. it became a second job.”

he is not the exception. he is the rule.

90% of personal wikis are abandoned within three months. not because people lose motivation. because the system breaks them.

there is a turning point that happens to every second brain. maintenance cost crosses value. you spend more time filing than thinking. more time updating than using. the library gets bigger and slower at the same time.

the compiler architecture flips this.

raw holds the source materials. unstructured. immutable. ground truth. wiki is where the model converts everything in raw into structured, linked, evergreen knowledge. the human reads it. the model writes it. output is where finished work lands. built from compiled knowledge, not from memory.

at the center: CLAUDE.md. identity, preferences, goals, project context. the model reads it before every session. automatically. you never explain yourself again.

the loop closes through update. every new source gets ingested, compiled, linked, and integrated. the system improves with every cycle automatically.

five automations run the whole thing. ingest captures and extracts. write retrieves and drafts. manage links decisions to context. review summarizes and reflects. maintain prunes and improves.

the researcher who abandoned his second brain was doing all of this by hand. every link. every tag. every update. every contradiction check.

the compiler does it for him now.

retrieval answers questions. compilation builds understanding.