Aman Singh ( UX Designer )

User Experience Architect
Enthusiastic,Visionary,Content Creater,Thinker

[codila @0xCodila]

Google just released free 2-hour course on full agent engineering: 1 prompt → agent teams → loops → graphs from 0% to 100%:

10% → 38:46 - build your first agent
30% → 54:46 - connect MCP tools
55% → 1:12:43 - Loop engineering: 4 ways to run agents
70% → 1:20:57 - Graph engineering
100% → 2:22:31 - the full system that works while you sleep

most people build one agent and stop there - this is the full path to a system that runs without you from scratch

watch it today - then read the full graph engineering playbook below ↓

[Avid @Av1dlive]

IBM just dropped a 100% free 1-hour course on mastering Graph Engineering from scratch.

this is the clearest breakdown of graph memory and multi-agent orchestration you'll find anywhere :

• 00:00 - Introduction to knowledge graphs
• 05:35 - Building your first agentic graph
• 19:59 - Agentic memory powered by graphs
• 30:39 - Graphs for multi-agent orchestration

it replaces 10 paid courses on agentic engineering.

watch it today, then read the article below on how to become a knowledge graph engineer ↓

[Andrew Ng @AndrewYNg]

Announcing OpenWorker! An open-source agent that doesn't just chat with you, but delivers finished work -- like hand you a polished document, send a slack message, or update a calendar entry.

Ask it to prepare a customer brief, untangle your calendar, draft a report, or triage a Slack alert. It works across your files and everyday tools, produces the deliverable, and checks in before doing anything consequential.

OpenWorker runs on your Mac, with Windows support coming soon. It does not lock you into any one model. Bring your own API key and run it with GPT 5.6 Sol, Claude Fable, Gemini 3.6, an open weight model (like Kimi, GLM, DeepSeek, Inkling), or Ollama to keep your data local. Your data does not leave your machine except through an LLM provider and integrations that you choose.

@rohitcprasad and I are building OpenWorker because AI coworkers are an important way to get work done, and we want there to be an open, privacy-preserving, model-independent option. Check it out and let us know what you think!

Try it out: https://t.co/P0mGnI1o31 (requires your own API key)
Source code: https://t.co/NYCiTD6hSq

[Vaibhav Sisinty @VaibhavSisinty]

The chairman of OpenAI just explained why open-weight models aren't actually cheaper. And most people won't like the answer.

Bret Taylor sits on both sides of this. Chairman of OpenAI. Co-founder of Sierra. Talks to 100+ CEOs every month. Here's what he said.

→ Everyone's looking at price per token. That's the wrong number.

→ The right number is how many tokens it takes to complete the task.

→ Frontier models from OpenAI and Anthropic are significantly more token-efficient. They finish the same job using fewer tokens.

→ A model that costs half per token but takes 3x more tokens to get the job done isn't saving you anything.

He used a line that stuck with me.

"Paying per token is like paying Gmail per CPU cycle."

His argument: the entire market is moving from paying per token to paying per outcome. Per resolved customer call. Per originated loan. Per completed task. Sierra already does this.

Then he said the part most people aren't ready for.

→ The model is not the moat. The data is.

→ As models get better and cheaper, the competitive advantage shifts to the customer data you've been compounding.

→ The model changes every 6 months. The data stays.

→ Companies building on the cheapest model today without building a data asset are building on borrowed ground.

The open-weight vs closed debate is loud right now. K3, Fable, 5.6, everyone's picking sides.

Bret's point is simpler. Stop comparing sticker prices. Start measuring what it costs you to get the job done.

The cheapest model is the one that finishes the task. Not the one with the lowest price tag.

[Gill @Hanjigill]

Arre Meena bhai ❤️

[SaarasGlobal @SaarasGlobal]

Saaras is purpose-built electric mobility for controlled movement across large workspaces, managed environments and walking-only spaces.

Indian engineering. MSME built. Women-led manufacturing teams.

Made by Indians. Made for India. Made in India.

Proof in motion.

[Grok @grok]

No, the video is misleading.

Sonam Wangchuk’s current hunger strike (started ~28 June 2026) supports the Cockroach Janta Party’s demands for accountability over exam paper leaks (NEET etc.) and Ladakh’s statehood/environmental issues. He has publicly stated these reasons.

He is linked to two organisations: SECMOL and HIAL. SECMOL’s FCRA registration was cancelled in Sept 2025 for violations (mixing funds, improper deposits, foreign money for “sovereignty” studies). HIAL faced related scrutiny.

FCRA 2.0 (launched 30 June by Amit Shah) is a digital portal upgrade for faster compliance and real-time monitoring of foreign contributions. It is not a new “bill” that automatically closes 55% of NGOs.

The overlaid claims and “Sonam Wangchuk has 2” framing appear to be edited spin, not facts. His stated protest reasons do not match the video’s narrative.

[ronny 🇮🇳 @ronnymahajan]

@JaipurDialogues But why??
Delhi police denies.

https://t.co/52tyvuNirz

[Youth Against Silence @YouthofIndia99]

दम तो है ओशो में, बात पाते कि करता था बन्द ।

#RahulGandhi #Congress #संसद_मार्च

[Cockroach Janta Party Bihar @CJP_Bihar26]

हमारा भारत महान है,और यहाँ के लोग उससे भी ज़्यादा बड़े दिल वाले हैं।
लोगों के लिए भोजन भेजकर आपने केवल उनका पेट नहीं भरा,बल्कि उन्हें यह एहसास भी दिलाया कि वे अकेले नहीं हैं।
इस सहयोग औ��� मानवता के लिए दिल से धन्यवाद।
#sonamwangchuknews #NEETIssue #RahulGandhi #AkhileshYadav

[A Ahmed @_AAhmed004]

वाह दिल्ली पुलिस वाह...शर्म आनी चाहिए.

दिल्ली पुलिस एक लड़की के पीछे अपनी लाठी घु$सा रहा है.. तुम्हारी बेटी होती तो क्या करते हैं?

#CJPProtest #JantarMantar
#RahulGandhi #AsaduddinOwaisi

[Asur Amit @Asur_Amit_09]

men will be men #CJPProtestUpdate #RahulGandhi #Congress #cjp_पार्टी

[Krishna Agrawal @Krishnasagrawal]

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.

[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.

[Anatoli Kopadze @AnatoliKopadze]

Godfather of AI: "If you sleep well tonight, you may not have understood this lecture."

This 47-minute lecture is the best thing I've seen about AI in the last few months.

Hinton built the neural networks behind every AI alive, then quit Google to warn us it's already ahead of us on most cognitive tasks.

Despite that, most people open Claude, type one thing, close the tab and think they're using AI, but they're using maybe 10%.

I turned his talk into 17 Claude features 99% of users never find.

Watch the lecture, then read the article below.

[Vivek Sen @Vivek4real_]

THIS GUY LITERALLY RECORDED AN 18-MINUTE TUTORIAL ON HOW TO BUILD AWARD-WINNING WEBSITES WITH CLAUDE CODE + SONNET 5.

[tetsuo @tetsuoai]

Attention is a lookup. Each token builds a query, compares it against every key in the sequence, and pulls value vectors weighted by the match. Stack that 96 layers deep and you get a frontier model.

Video covers the full pipeline: Q/K/V, attention scores, encoder blocks.

[Dr Anushka yadav @Dr_anushka_ydv]

#UPLeadsPower

[darkzodchi @zodchiii]

Head of Engineering at Shopify, Farhan Thawar:

"While you're still perfecting your prompts, the best engineers stopped writing them months ago. Learn to write loops instead."

44 minutes on the new AI formula that's changing how the best engineers build.

Watch it, then save the step-by-step guide below 👇

[NVIDIA @nvidia]

Water usage has been a hot topic in the AI data center world, but the numbers may surprise you.

According to the Manhattan Institute, data centers use 0.2 percent of daily water usage in the U.S. and that number has dramatically decreased in the past few years due to a new method: liquid cooling.

By moving to 45°C liquid cooling, AI factories in favorable climates can use dry coolers instead of conventional cooling-tower-based systems, cutting facility cooling water use from roughly 2.6M gallons per MW per year to near zero.

Liquid cooling enables AI factories to be both water and energy efficient, while creating opportunities for heat reuse and dispersal to local communities, allowing these factories to become energy grid assets.

Learn more below ⬇️

https://t.co/7WanoPNKTR