Notarize

One world. One chain

[Notarize @Notarize16]

Agents

[Alfie Carter @AlfieJCarter]

R.I.P. rebuilding your GTM stack from scratch every session.

A complete Claude Skill Library can replace a $15,000/month agency retainer.

It is not as easy as hiring someone else to do it.

But if you start today, you can have 56 skills loaded into Claude covering SEO, content, outbound, sales, growth, analytics, strategy, ads, social, and CRM by end of this week.

I usually charge $299 for access to this library but today, it's free.

Like this post + comment 'Agents' and I'll DM you the entire skill library for free.

(Must be following, or I can't message.)

Taking this down in 48 hours.

[Notarize @Notarize16]

@selinatasnim1 Agent

[Andrej Karpathy @karpathy]

Three days ago I left autoresearch tuning nanochat for ~2 days on depth=12 model. It found ~20 changes that improved the validation loss. I tested these changes yesterday and all of them were additive and transferred to larger (depth=24) models. Stacking up all of these changes, today I measured that the leaderboard's "Time to GPT-2" drops from 2.02 hours to 1.80 hours (~11% improvement), this will be the new leaderboard entry. So yes, these are real improvements and they make an actual difference. I am mildly surprised that my very first naive attempt already worked this well on top of what I thought was already a fairly manually well-tuned project.

This is a first for me because I am very used to doing the iterative optimization of neural network training manually. You come up with ideas, you implement them, you check if they work (better validation loss), you come up with new ideas based on that, you read some papers for inspiration, etc etc. This is the bread and butter of what I do daily for 2 decades. Seeing the agent do this entire workflow end-to-end and all by itself as it worked through approx. 700 changes autonomously is wild. It really looked at the sequence of results of experiments and used that to plan the next ones. It's not novel, ground-breaking "research" (yet), but all the adjustments are "real", I didn't find them manually previously, and they stack up and actually improved nanochat. Among the bigger things e.g.:

- It noticed an oversight that my parameterless QKnorm didn't have a scaler multiplier attached, so my attention was too diffuse. The agent found multipliers to sharpen it, pointing to future work.
- It found that the Value Embeddings really like regularization and I wasn't applying any (oops).
- It found that my banded attention was too conservative (i forgot to tune it).
- It found that AdamW betas were all messed up.
- It tuned the weight decay schedule.
- It tuned the network initialization.

This is on top of all the tuning I've already done over a good amount of time. The exact commit is here, from this "round 1" of autoresearch. I am going to kick off "round 2", and in parallel I am looking at how multiple agents can collaborate to unlock parallelism.
https://t.co/WAz8aIztKT

All LLM frontier labs will do this. It's the final boss battle. It's a lot more complex at scale of course - you don't just have a single train. py file to tune. But doing it is "just engineering" and it's going to work. You spin up a swarm of agents, you have them collaborate to tune smaller models, you promote the most promising ideas to increasingly larger scales, and humans (optionally) contribute on the edges.

And more generally, *any* metric you care about that is reasonably efficient to evaluate (or that has more efficient proxy metrics such as training a smaller network) can be autoresearched by an agent swarm. It's worth thinking about whether your problem falls into this bucket too.

[Notarize @Notarize16]

@Suryanshti777 Code

[Suryansh Tiwari @Suryanshti777]

🙀This is Insane: You can run Claude Code completely free now.

No API bills.
No rate limits.
No data leaving your device.

Just Claude Code running locally fast, private, and 100% yours. Here’s how to set up Claude Code on your own machine (free + fully private)

For guide: Local AI Coding Setup: Free Claude-Like Agent (Ollama + VS Code)

How to get:
Follow me MUST (so I can dm you)
Like + RT
Comment "Code"

[Two Cents Daily @twocents_daily]

McConaughey just explained capitalism better than most economists.

every major moral panic in history followed the same arc — outrage, debate, legislation, adoption. the printing press, electricity, the internet. people protested each one. capital won every time.

AI isn't different. it's just faster.

the real signal isn't that the moral debate will disappear. it's that it becomes irrelevant while it's still happening. regulation will lag by 10 years. deployment will lag by 10 months. the gap between those two timelines is where every major AI fortune gets built.

McConaughey's actual advice — trademark your voice, own your likeness — is the most practical thing any creative professional has heard this year. not because AI is wrong, but because it's unstoppable and the only question left is whether you're protected when it arrives.

moral arguments don't stop technology. they just determine who gets left behind.

[Notarize @Notarize16]

@free_ai_guides Anthropic

[Notarize @Notarize16]

@heygurisingh Claude

[Lior Alexander @LiorOnAI]

Repo: https://t.co/cmk6fVy7U1

[Lior Alexander @LiorOnAI]

Stop storing embeddings.

A laptop can now index 60 million text chunks using 6GB, not 200GB.

LEANN, a new open-source project flips how vector search works.

𝗧𝗵𝗶𝘀 𝗶𝗻𝗱𝗲𝘅 𝗱𝗼𝗲𝘀 𝗻𝗼𝘁 𝘀𝘁𝗼𝗿𝗲 𝗲𝗺𝗯𝗲𝗱𝗱𝗶𝗻𝗴𝘀
Instead of saving every vector, it stores a compact graph.
Embeddings get recomputed only when a query actually needs them.

• Graph-based selective recomputation
• High-degree node pruning to keep recall stable
• No accuracy drop versus FAISS-style indexes

𝗧𝗵𝗲 𝘀𝘁𝗼𝗿𝗮𝗴𝗲 𝗴𝗮𝗶𝗻𝘀 𝗮𝗿𝗲 𝗺𝗮𝘀𝘀𝗶𝘃𝗲
Email archives shrink from gigabytes to megabytes.
Browser history fits in single-digit MBs.
A 60M-document corpus fits on a laptop SSD.

𝗜𝘁 𝗿𝘂𝗻𝘀 𝗲𝗻𝘁𝗶𝗿𝗲𝗹𝘆 𝗹𝗼𝗰𝗮𝗹
No cloud calls. No telemetry.
Everything stays on-device with zero ongoing cost.

𝗜𝘁 𝘂𝗻𝗹𝗼𝗰𝗸𝘀 𝗹𝗼𝗰𝗮𝗹 𝗥𝗔𝗚 𝗮𝘁 𝗻𝗲𝘄 𝘀𝗰𝗮𝗹𝗲
You can semantically search files, emails, chats, codebases, and live MCP sources.
All from one local index, without changing your workflow.

[Notarize @Notarize16]

https://t.co/CgY0Ly5C7k

[Notarize @Notarize16]

@atikcoder0 DS

[Notarize @Notarize16]

@atikcoder0 Agent1

[Notarize @Notarize16]

@godofprompt AI

[Notarize @Notarize16]

GEMINI

[Lian Lim | Dashboard & AI Automation Expert @dashboardlim]

gemini 3 pro is google's smartest model

n8n is the easiest automation platform

together, they can make up workflows that cost $10k-20k

the integration lets you:
→ build AI agents with little or without code
→ automate image and document processing
→ create complex workflows in minutes
→ configure thinking levels and API settings

i made a playbook that covers everything on:
- gemini 3 pro + n8n setup
- building decision-making agents
- advanced configs nobody talks about

most people don't know this exists yet

learn it before they do

comment "GEMINI" and i'll send you the playbook for building AI workflows with gemini 3 pro and n8n

[Notarize @Notarize16]

Agent

[Ai With Piyas @piyascode9]

99% of the AI agent tutorials on YouTube are garbage.

I’ve built 47 agents with n8n and Claude.

Here are the 3 prompts that actually work (and make agent-building simple).

Bookmark this post
🔖
Bonus: comment "Agent: and I’ll DM you AI agent system prompt + full guide ↓

[Notarize @Notarize16]

SCRAPE

[Zephyr @Zephyr_hg]

Competitor research takes me 2 minutes now.

Built a scraper that monitors websites, tracks price changes, and extracts product data automatically.

Claude AI pulls contact info, pricing, and company details straight into Google Sheets.

Used to spend 10-15 hours monthly doing this manually.

Now it updates every hour while I focus on closing deals.

Comment "SCRAPE" and I'll DM it to you (must be following)

[Notarize @Notarize16]

@Zephyr_hg SCRAPE