Lumisky

Solo founder of AI account-keeping App. Share the building process here.

[Lumisky @ilumisky]

The temptation to quit will be greatest just before you are about to succeed.

[Google Antigravity @antigravity]

Here’s a roundup of some of the latest agent workflows, interactive demos, and build guides from our community 🧵

[Codez @0xCodez]

https://t.co/WVztfCUH4u

[h100envy @h100envy]

Google engineer explained how to fine-tune a tiny LLM from 46% to 90% accuracy on your phone in 21 minutes - better than $1500 on-device AI bootcamps.

pick Gemma 270M -> generate synthetic task data -> fine-tune with LoRA -> quantize to int4 -> deploy to Pixel and hit 2000 tokens per second.

That loop is how a 270M model beats a 70B one on your task, running fully offline in your pocket.

Gemma 270M + synthetic data + LoRA + int4 quantization + on-device runtime - that's the stack.

Watch and save it, then fine-tune your own tiny agent tonight.

[codila @0xCodila]

Anthropic and Andrew Ng built an agent that uses 90% fewer tokens from scratch:

they dropped the entire book of Frankenstein into a prompt - 108,000 tokens asked one question

the input dropped from 108,000 tokens to 11

here's how:

step 1 → put everything that never changes at the top - tools, then system, then docs

step 2 → mark where the static part ends. everything above it gets cached

step 3 → one stray space breaks it - and you pay full price again

step 4 → the cache dies in 5 min - every read resets the clock

step 5 → cached tokens don't count against your rate limits. free headroom

most people never touch this - it pays for itself on day one

watch & bookmark - this 1-hour brilliant course ↓

[Codez @0xCodez]

Andrew Ng just released a 2-hour course on building agentic skills from scratch with Anthropic:

• 00:00 – How to build agent skills with Claude
• 22:32 – Claude pre-built skills for AI agents
• 41:07 – Agentic skills vs tools, MCP, subagents
• 01:06:06 – Skills for long-running agents

This 2-hour watch will replace 10 paid courses on building agents, by Anthropic themselves.

Watch it today, then read how to build self-improving agentic systems in the article below.

[Codez @0xCodez]

Andrej Karpathy just dropped a 6-hour course on how to build LLMs from scratch:

• 00:00 - Deep dive into LLMs like ChatGPT
• 03:31:23 - Building ChatGPT from scratch in live
• 05:27:43 - How to use LLMs (Karpathy method)

This course will replace a $90K Stanford LLM master’s degree.

Start watching today, then read how to become an AI engineer in article below.

[Roan @RohOnChain]

My friend applied to 200 tech jobs in two years. No PhD. No Stanford.

Last month Anthropic offered him $750,000.

I asked him how he broke in from zero.

He sent me a course that was never supposed to get out. A 3-hour video to build a full LLM from scratch.

A developer teaches you exactly how LLMs like ChatGPT and Claude are actually built.

I watched it last night.

Halfway through, I realized it's embarrassingly simple to break into an AI lab.

Bookmark this and read the article below.

• 00:00 - intro to LLMs
• 05:43 - LLM transformer architecture
• 40:24 - training the LLM
• 1:30:27 - modernizing the LLM
• 2:33:53 - scaling the LLM

[Codez @0xCodez]

Google just dropped a 1-hour course on agentic engineering from scratch:

00:00 – How to build your first AI agent
08:24 – Build agent memory (short, persistent, long)
28:34 – Agentic loops, long-running AI agents
40:04 – How to build MCP (MCP vs API)
1:00:22 – Multi-agentic systems

This 1-hour watch will replace 10 paid agentic courses on the internet.

Watch it today, then read how to build a self-improving agentic system in the article below.

[Movez @0xMovez]

Andrew Ng just dropped a 3-hour course on how to become an AI Engineer in 2026:

• 00:00 - How to build agentic AI systems
• 04:25 - Future of AI engineering
• 23:38 - AI Prompting full course
• 2:52:17 - Creating an app with AI in 30 minutes

This 3-hour watch could replace 10 AI engineering courses on the internet.

Watch it today, then read how to run a self-improving system in the article below.

[Lumisky @ilumisky]

@NichtTK Nice joke!

[Paul Graham @paulg]

The users who complain about the flaws in your product may seem annoying, but they are on the whole probably your most valuable users. They complain because they care, and I doubt a startup could ever get really big without users who care a lot about the product.

[Philipp Schmid @_philschmid]

https://t.co/ALXlwGhCjP

[James Clear @JamesClear]

Your first attempt might not be very good, but nobody's early work is good. There will always be a gap between where you are and where you want to be. And the bridge between that gap is courage. The courage to look foolish in the beginning. The courage to show up again when your early work is criticized. The courage to look yourself in the mirror and say, "I realize I'm not good enough yet, but the only way to get better is to keep working on it."

[Naval @naval]

Good marketing is finding different ways to tell the truth.

[Reads with Ravi @readswithravi]

There’s an old Chinese proverb that I love:

“He who blames others has a long way to go on his journey. He who blames himself is halfway there. He who blames no one has arrived.”

[Yanhua @yanhua1010]

目前看到关于 “Agentic Engineering Workflow”的最完整的介绍👇

花了一个小时完整看完了，完全可以做成一个付费教程。

内容涵盖了tmux，agent记忆，skills，语音输入，长任务执行，并行worktree管理，多agent调度。

还有让���眼前一亮的可视化html编辑器Lavish和一套代码变更校验的流水线: no-mistakes

感谢作者@kunchenguid分享，值得每一个用ai agent的人收藏、学习。

[Lumisky @ilumisky]

@MaxForAI 你不知道的还有亚马逊。我前公司就是用亚马逊使用Claude Code。

[Reads with Ravi @readswithravi]

There's an old Chinese saying that I love:

“The temptation to quit will be greatest just before you are about to succeed.”

[Paul Graham @paulg]

Something I told 14 yo: Once you've prepared sufficiently for exams, switch your focus to "game management." Get enough sleep, keep calm, watch the time, check your answers to avoid dumb mistakes, etc.