AI.kemist (e/λ)

✨AI enthusiast 🧙🏼‍♂️Programming/Integration Wizard | Software Engineer 🤖 Into AGI/ASI. GPU poor

[Diego | AI 🚀 - e/acc @diegocabezas01]

Use Fable 5 as orchestrator and Opus + Codex to execute (to save fable usage):

Fable 5 (max reasoning) = orchestrator
Opus = deep reasoning subagent
Sonnet = mechanical work subagent
Codex = peer Sr. engineer, different perspective

Setup:
1. Set Fable 5 as your main model In Claude Code: /model → Fable 5 → reasoning /effort to max

2. Create 2 subagents with /agents In Claude Code:
deep-reasoner → pinned to opus "Use for reasoning-heavy phases, architecture, debugging complex issues, algorithm design. Think thoroughly, return a concise conclusion the orchestrator can act on."

fast-worker → pinned to sonnet "Use for mechanical tasks, boilerplate, tests, formatting, simple edits. Execute efficiently."

3. Add OpenAI's official Codex plugin (install codex cli in your computer first), In Claude Code type:
/plugin marketplace add openai/codex-plugin-cc
/plugin install codex@openai-codex
/codex:setup

4. Drop this in your CLAUDE.md in your folder:

## Orchestration workflow
You (Fable) are the orchestrator. Plan, decompose, synthesize.
Reasoning-heavy phases → deep-reasoner
Mechanical work → fast-worker
Codex (/codex:rescue --background) is a cracked engineer on par with deep-reasoner, from a different perspective. Treat as a peer, not a reviewer.
High-stakes decisions: task Opus + Codex on the same problem in parallel, synthesize the best of both, without showing either the other's answer. Keep your own context lean.

5. Then prompt Fable like a tech lead: "Goal: [what you want] Context: [files, constraints] You're the lead. Delegate reasoning to deep-reasoner, grunt work to fast-worker, fresh-perspective problems to Codex. Show me your plan first, then execute."

That's it.

[Path of Men @PathOfMen_]

Brush your teeth with your non-dominant hand. it stimulates neuroplasticity, creates new neural connections, and boosts your cognitive flexibility.

[sidraa♡ @its_sidraa]

- Claude = coding. ($20/mo)
- Supabase = backend. (Free)
- Vercel = deploying. (Free)
- Namecheap = domain. ($12/yr)
- Stripe = payments. (2.9%/transaction)
- GitHub = version control. (Free)
- Resend = emails. (Free)
- Clerk = auth. (Free)
- Cloudflare = DNS. (Free)
- PostHog = analytics. (Free)
- Sentry = error tracking. (Free)
- Upstash = Redis. (Free)
- Pinecone = vector DB. (Free)

Total monthly cost to run a startup: ~$20

There has never been a cheaper time to build.

[HIDEO_KOJIMA @HIDEO_KOJIMA_EN]

1/2
Eventually, even digital data will no longer be owned by individuals on their own initiative. Whenever there is a major change or accident in the world, in a country, in a government, in an idea, in a trend, access to it may suddenly be cut off.

[AI.kemist (e/λ) @TheAIkemist]

@PlayStation @iHuGi WTFFF???!!! NOOOO

[Soccer Media™⚽ @SoccerMediaX]

Bro how could anyone hate this guy!! 😭😆😂

[Ronin @DeRonin_]

My entire AI stack is now Chinese 🇨🇳

87% cheaper. same revenue

swaps by task:

1. reasoning / backend brain
Opus 4.8 → Kimi K2.7
benchmark gap: ~8% · price: ~11x cheaper

2. code generation
GPT-5.5 → Qwen 3.7 Max
benchmark gap: ~18% · price: ~7x cheaper

3. agent loops + tool calling
Sonnet 4.7 → GLM 5.2
benchmark gap: ~3% · price: ~5x cheaper on input

4. cheap volume / bulk processing
GPT-5.5 mini → MiMo V2.5
benchmark gap: ~6% · price: ~12x cheaper

5. image generation
GPT-Image-2 → Wan 2.5
benchmark gap: ~5% · price: ~8x cheaper

6. video generation
Sora 2 → Kling 3.0
benchmark gap: roughly equal · price: ~6x cheaper

[ result after 30 days: ]

operating costs dropped 87%, output quality dropped 4% on average, revenue unchanged

the most important that these models will be not banned in a month and i can run them locally

nobody will steal my data and i can learn them as i need

full article drops tomorrow with:
> exact routing logic per task type
> the 2 cases where I still pay for American
> the migration playbook anyone can copy in a weekend

VERY IMPORTANT to get migrated now, while it's not too late

[monokern @monokern]

HE BUILT A $10,000-TIER ANIMATED SITE WITH CLAUDE CODE - FOR THE COST OF A SUBSCRIPTION

What's on screen isn't a landing page with a parallax background

It's a fully interactive, scroll-driven site with real-time 3D rendered in the browser

What's actually on the page:
> 3D product models rotating and reacting to scroll in real time via WebGL
> Smooth hover interactions and transitions - no hand-coded keyframes
> Cinematic minimal aesthetic that got featured on Awwwards
> Typography layering, editorial layouts, everything assembled in one session

What it normally takes:
> A 3D artist, a motion designer, and a frontend developer
> Weeks of handoffs - modelling, exporting, wiring animations, layout, copy
> Six separate systems integrated by hand

That pipeline was the moat. It's what justified the invoice

The price gap:
> Studio build at this level: $5,000-10,000+
> Your cost: a Claude subscription

Timeline:
weeks of production -> a single session

Full walkthrough in the article below

[West Lord @MyWestLord]

Karpathy method + Claude Code reading your whole Obsidian vault is the smartest second brain on earth.

The method is simple and brutal. If you can’t build a thing from scratch, you don’t know it. Tutorials are fake learning and your brain deletes them in 3 days.

Most people ignore this. They build a second brain that just sits there, folders of notes nobody reopens, dead text.

Point Claude Code at the vault and it wakes up. 5,000 notes, one mind. It reads all of it and answers in your own words and your own proofs, not a model’s guess.

Then the loop closes.

Want to understand neural nets? Skip the 3-hour video and ask Claude Code to build a tiny one. 200 lines from scratch. Watch it train, break a layer, watch it fail, fix it.

It clicks in 20 minutes instead of 3 weeks.

The second it lands the note gets written. One idea per file, linked to 10 others, dropped into the vault while the memory is still hot.

Now it compounds.

Month 1: is 60 notes. Month 6 is 900. Every new note pulls in old ones, so you ask anything and the answer comes from your brain, not the internet.

Before: 40 tabs, 6 half read PDF, 0 retained.

After: build it once, own it for life.

Setup takes 4 minutes. Plain text, no lock-in.

A second brain nobody reads is a graveyard.

Yours just started thinking.

[CyrilXBT @cyrilXBT]

KARPATHY’S CLAUDE + OBSIDIAN WORKFLOW MAKES YOUR NOTES A SELF-RUNNING SECOND BRAIN.

No hand-sorting. No Sunday “inbox zero” rituals.

Toss any article, PDF, or clip into one folder.

Claude ingests it, connects it to what you’ve already captured, and shelves it inside a living wiki.

Every new drop makes the vault sharper—while you do none of the busywork.

This is the shift: stop treating AI like a code monkey and start using it as a thinking engine.

Save this. Follow @cyrilXBT

[CyrilXBT @cyrilXBT]

I genuinely don't understand why everyone isn't using this yet.

Andrej Karpathy, OpenAI co-founder, posted a simple idea that went massively viral:

Stop using AI to write code.
Use it to build a second brain.

You point Claude Code at a folder. Drop in any source: an article, a transcript, a PDF.
Claude reads it, links it, files it into a living wiki of everything you know.

It compounds like interest. The more you feed it, the smarter it gets.

Here's the whole thing:

1) Install Obsidian
2) Create a vault
3) Open it in Claude Code
4) Paste Karpathy's wiki idea and tell Claude to build it
5) Claude makes three folders:
- raw (for sources)
- wiki (for its pages)
- CLAUDE. md (that runs it)
6) Drop any source into raw and say: "ingest this"
7) Ask questions across everything, forever

Five minutes to set up and you never start from a blank chat again.

Full step by step guide below.

[Nav Toor @heynavtoor]

10 GitHub repos that defined 2026 so far.

Bookmark this list.

1. OpenClaw
Peter Steinberger went from 9,000 to over 300,000 stars in months. Personal AI assistant that runs entirely on your devices. Steinberger joined OpenAI shortly after.
Repo → https://t.co/9B3jxI7HwY

2. anthropics/skills
135,000 stars. The patterns Anthropic uses internally to extend Claude. The repo that defined the skills ecosystem of 2026.
Repo → https://t.co/6VBUdubDG0

3. affaan-m/everything-claude-code
141,000 stars. The complete library of Claude Code skills, agents, and commands. The aggregator every serious builder forks.
Repo → https://t.co/PaXno1QqDi

4. andrej-karpathy-skills
Forrest Chang built a single CLAUDE md file in January. 109,000 stars. The most starred single-file repo in GitHub history.
Repo → https://t.co/unItpr073y

5. Hermes Agent
Nous Research released this in February. 105,000 stars. The self-evolving AI agent that gets smarter the more you use it.
Repo → https://t.co/OMgRfKAts4

6. obra/superpowers
94,000 stars. Officially accepted into Anthropic's skills marketplace. Multi-agent orchestration without the boilerplate.
Repo → https://t.co/Z7i3fzf4s4

7. claude-task-master
Multi-agent orchestration on top of Claude Code. Turn one prompt into a coordinated team of specialists shipping a feature while you sleep.
Repo → https://t.co/0xYzJpSX4z

8. MemPalace
Milla Jovovich, the actress from Resident Evil, co-built this with Ben Sigman using Claude Code. Near-perfect score on the LongMemEval benchmark.
Repo → https://t.co/o8xKSTz60D

9. karpathy/autoresearch
Andrej Karpathy released his own research automation framework. 23,000 stars in three days. The closest thing to having Karpathy as your research partner.
Repo → https://t.co/YURNnYJJN3

10. karpathy/nanochat
Karpathy released a complete pipeline to train a ChatGPT from scratch for $100. 54,800 stars. The best ChatGPT money can buy is the one you train yourself.
Repo → https://t.co/BZYF0qXE9z

Save this. Share it with the developer in your life who deserves to know what they missed.

100% free. 100% open source.

[CyrilXBT @cyrilXBT]

https://t.co/alKJ5Gf6LV

[Yarchi @undefinedKi]

https://t.co/KADozFhjGF

[Ornith @ornith_]

Aloha! 🌺 Meet Ornith-1.0, a family of open-source LLMs specialized for agentic coding.

Ornith-1.0 spans the full parameter sizes including 9B Dense, 31B Dense, 35B MoE, and 397B MoE. It achieves state-of-the-art performance among open-source models of comparable size on coding benchmarks including:
✅Terminal-Bench 2.1(77.5)
✅SWE-Bench(82.4 on verified, 62.2 on pro, 78.9 on Multilingual)
✅NL2Repo(48.2)
✅SWE Atlas(41.2 on QnA, 42.6 RF, 39.1 TW)
✅ClawEval(77.1)

Post-trained on top of gemma4 and qwen3.5, Ornith-1.0 employs a novel self-improving training strategy in which reinforcement learning is used to generate not only solution rollouts, but also the task-specific scaffolds that drive those rollouts. By jointly optimizing the scaffold and the resulting solution, the model generate higher-quality solutions in agentic coding.😎

All models are released under the MIT license, enabling full commercial and research use.

📖Tech Blog: https://t.co/qT9N2HYWFn
🤗Huggingface: https://t.co/PRrwqjeBtM

[Harrison Kinsley @Sentdex]

just stop sending them your money.

use openrouter for a month.

I guarantee you the doomerism would suddenly vanish.

[Teknium 🪽 @Teknium]

@NousResearch Docs on how to setup your own custom mixture of models here:

https://t.co/Urk4SOsLUW

[AI With Shipon @Shipon_40AI]

Goodbye Claude Code subscription fees.

Someone just built a proxy that runs Claude Code completely free... and it's wild.

You literally plug in a free NVIDIA API key and point Claude Code at localhost.

That's it.

It handles everything:
- Converts Anthropic API calls to NVIDIA NIM format
- Unlocks 40 requests/min for free
- Supports Kimi K2, GLM 4.7, MiniMax M2, Devstral and more
- Streams thinking tokens and tool calls live
- Even includes a Telegram bot so you can run Claude Code from your phone

No API bill. No rate limit panic. No vendor lock-in.

Honestly, this goes beyond router tools like OpenRouter.

It doesn't just swap the model... it turns Claude Code into a free agent you can control remotely.

The project is open-source on GitHub.

It's called free-claude-code.

[老杨啊 @yhslgg]

卧槽，14.8万星！TypeScript大神把几十年工程经验直接做成了Claude Code的Skill

Matt Pocock——就是那个 TypeScript 界封神的老哥——把自己 .claude 目录里的东西开源了。

一行命令安装：

npx skills@latest add mattpocock/skills
然后在 Claude Code 里你就有了这些：🔥

/tdd — 强制红绿重构循环，AI写代码必须先写测试，不让它自由发挥

/diagnosing-bugs — 结构化 Bug 诊断，复现→最小化→假设→验证→修复，一步不跳

/grill-with-docs — 需求对齐，让 AI 在动手之前先建立项目的领域模型，不再鸡同鸭讲

/to-prd — 把对话直接变成 PRD 扔进你的 Issue 追踪器

/handoff — 上下文压缩成交接文档，下一个 Agent 直接接着跑

/improve-codebase-architecture — 扫架构问题，出 HTML 报告

他在 README 里写了一句话：这是给真正的工程师用的，不是氛围编程（vibe coding）。

特么的说到我心坎里了😂

AI写代码快是快，但代码质量烂，测试没有，架构是泥球，这些问题这套 Skill 都在帮你堵。

14.8 万星不是吹出来的，是真的有用。

https://t.co/X4uV3FbUT7

[CyrilXBT @cyrilXBT]

KARPATHY'S SECOND BRAIN PATTERN TURNS YOUR NOTES INTO SOMETHING YOU CAN ACTUALLY SEE.

Not a folder.

Not a list.A graph.

Hundreds of nodes, color coded by domain, linked in patterns you never planned by hand.

Run Claude Code against an Obsidian vault for 30 days and the graph view stops looking like a notebook and starts looking like a map of how you actually think.

This is what happens when a second brain stops being storage and starts being a structure.

Bookmark this. Follow @cyrilXBT