Alee

A web techy who tweets abt web technology, big data analytics,online marketplaces, and global sourcing trends

[Google Cloud Tech @GoogleCloudTech]

🎉 We're expanding @antigravity for enterprise customers!

Read how this expansion will help even more eligible Gemini Enterprise customers and developers accelerate software delivery—with the security and control organizations need to innovate at scale → https://t.co/3PYG4u6BiW

[Google Gemini @GeminiApp]

Back-to-school season is here and starting today, eligible college students can get a full year of Gemini on us:
- US students: 1 year of Google AI Pro at no cost
- 140+ countries: 1 year of Google AI Plus at no cost

Here’s what’s new for students �Back-to-school season is here and starting today, eligible college students can get a full year of Gemini on us:
- US students: 1 year of Google AI Pro at no cost
- 140+ countries: 1 year of Google AI Plus at no cost

Here’s what’s new for students �Back-to-school season is here and starting today, eligible college students can get a full year of Gemini on us:
- US students: 1 year of Google AI Pro at no cost
- 140+ countries: 1 year of Google AI Plus at no cost

Here’s what’s new for students �Back-to-school season is here and starting today, eligible college students can get a full year of Gemini on us:
- US students: 1 year of Google AI Pro at no cost
- 140+ countries: 1 year of Google AI Plus at no cost

Here’s what’s new for students �Back-to-school season is here and starting today, eligible college students can get a full year of Gemini on us:
- US students: 1 year of Google AI Pro at no cost
- 140+ countries: 1 year of Google AI Plus at no cost

Here’s what’s new for students �Back-to-school season is here and starting today, eligible college students can get a full year of Gemini on us:
- US students: 1 year of Google AI Pro at no cost
- 140+ countries: 1 year of Google AI Plus at no cost

Here’s what’s new for students 👇

[Mr. Buzzoni @polydao]

NVIDIA is giving away free access to 140+ AI models for a full year

> a lot of people building agents are paying $50-200/month just for API access

NVIDIA just made that argument irrelevant

models you get: GLM 5.2, MiniMax M3, Nemotron-3.5-lightning-30b-a3b, Muse-glimmer-30b from Meta and 130+ more

setup:

> step 1 - get your free key
> go to https://t.co/9OAPVB6SrM
> register -> bind phone -> copy API key

> step 2 - add to Hermes agent
> open Settings -> Model Provider -> Custom

base_url = "https://t.co/ndvYuRyWSB"
api_key = "nvapi-xxxxxxxxxxxxxxxxxxxx"

> step 3 - pick a model

model = "z-ai/glm-5.2"
model = "minimaxai/minimax-m3"
model = "nvidia/nemotron-3-ultra-550b-a55b"
model = "moonshot-ai/kimi-k2.7"

> Hermes already has NVIDIA set as default base_url
> paste the key and you're running instantly
> works the same in Cursor and OpenCode

> cost: $0
> limit: 40 req/min
> expires: 1 year

a free key changes what you can afford to run:

> one prompt costs nothing either way
> a loop firing 300 agents every week is where the bill shows up
> for a year that bill is zero

40 req/min becomes your fan-out limit. the only thing left to design is the loop itself

full stack i built on top of it - trigger, gate, typed graph, corrections carried between runs - is linked below

[Bloomberg @business]

China is rapidly catching up to the US in the AI race, especially on price.

But how do Chinese models compare in quality? We put seven models to the test by asking each to build a website for a coffee shop https://t.co/BKnXPNdeks

[Ricker @0xRicker]

300 agents without context engineering is just 300 ways to lose track of the answer.

a serious agent system starts looking less like:

1 model → 1 prompt → 1 answer

and more like:

1 planner → N parallel agents → verifier → merge → memory → human gate

once you have 10, 50, or 300 agents, the number of possible relationships explodes.

100 entities = 4,950 possible pairwise relationships.
300 = 44,850.
1,000 = 499,500.

that’s why “just give the model more context” stops working surprisingly fast.

you need different agents seeing different slices of the graph.

the architecture around the model is becoming the product.

full article below ↓

[Google Gemma @googlegemma]

https://t.co/4VCOeP9yN1

[Google @Google]

When we first introduced @GoogleGemma, our family of open models, our goal was to give developers the tools to build responsible, innovative AI applications anywhere. Today, Gemma models have surpassed a billion downloads. 🎉

Over the past two years, developers have published over 100,000 Gemma model variants and built a thriving innovation ecosystem we call the Gemmaverse.

We’re taking a look at how the Gemmaverse is making an impact across the globe ↓🧵

[the0xbt @the0xbt]

Andrew Ng co-founded Google Brain taught half this industry its first AI course:

"Prompting will be dead in just 6-9 months, graphs are what's replacing it".

Agents -> Loops -> Graphs -> Self-Improving Systems

The first 15 minutes already cover what most $1,000 courses skip entirely.

> A prompt buys you one answer.
> A graph buys you a system that runs when you don't.

This free lecture beats most paid agent engineering programs.

Watch it today, then read the guide below on systems that improve themselves ↓

[J.B. @VibeMarketer_]

call me crazy but the first AI agent most companies should build is an autonomous analyst.

you can build one using Kimi K3.

it watches your competitors while you sleep, remembers every move, and wakes your team with the launches, pricing changes, and positioning shifts they need to act on.

don't bookmark this if it crosses your timeline.

paste the full article into Kimi and tell it to build the first version for your market.

[Google Cloud @googlecloud]

Agentic AI demands strong data foundations. Our new report with MIT Technology Review Insights details how leaders are getting their data estates ready for the era of autonomous agents.

Learn more insights from "Scaling AI agents with trustworthy data" → https://t.co/1KtUSo3YbZ

[the0xbt @the0xbt]

A Chinese developer explained the shift from Loop Engineering to Graph Engineering better than anyone in English:

"The value of a graph comes from its determinism, not from the number of agents".

In 21 minutes he covers the four parts of a graph and Anthropic's five workflow patterns.

Prompts -> Loops -> Agents -> Graphs

A single-agent loop goes "goal blind" and keeps running anyway.

A graph fixes that with verifiers and fallbacks, not with more agents.

This one video covers more than most $1,000 agent engineering courses.

Watch it now, then lock in the full A-Z guide below ↓

[Mahax @Mahaximus_]

Google just dropped a 1-hour course on full AI engineering: from 1 agent to Loops and Graphs

7:02 - Build your first agent
13:34 - What agents can do
23:08 - Context engineering
32:56 - Graph engineering
54:11 - Full autonomous system

One agent saves you an hour. A thousand replaces the team.

Watch it, then read the full guide on loops and graphs below

[Google for Developers @googledevs]

Static PDF ➡️ interactive web app, all in one prompt!

We used Gemini 3.7 Flash in @GoogleAIStudio to transform a dense PDF annual report into a beautiful website. Using its native PDF understanding, the model easily extracted data, crunched the numbers, and generated delightful interactive UI in one go.

Learn how from @genevieve__h:

[Anatoli Kopadze @AnatoliKopadze]

Head of Claude Code:

"85% of our engineers are running dozens or hundreds of agents. The way you do it is graph engineering."

In 40 minutes he explains how a single engineer now does the work of a whole team, how far this has gone inside Anthropic and where it goes next.

This is something you can't skip if you don't want to be left behind.

Watch it, then read the full guide on graph engineering below.

[Hanako @hanakoxbt]

ANTHROPIC LEAKED A 4-AGENT SETUP THAT CUTS A CODEBASE AUDIT FROM 3 DAYS TO 20 MINUTES

you point it at a repo and walk away - it comes back with what breaks, ranked, patches already tested.

repo → map → 4 auditors → rank → fix → verify → report → back into the map

the map cuts the repo by blast radius, not by folder - skip it and four agents audit the same three files and miss the one that ships broken.

4 auditors run in parallel with separate contexts - deps, secrets, dead code, hot paths, and none of them sees another's findings.

rank is code, not an agent - sort by what breaks production, drop the duplicates, zero tokens.

the fixer only opens patches for the top slice - a hundred findings nobody acts on is a report, not an audit.

verify runs the suite on every patch and red goes back to the fixer - that patch only, never the whole batch.

the back edge into the map is the whole trick - accepted findings become rules, so next week starts where this one ended.

one human step in all of it: which fixes ship - 20 minutes instead of 3 days.

save this and read the full graph engineering course below ↓

[rari @0xwhrrari]

Anthropic engineer:

"90% of our engineers were already running self-improving loops

Now everyone is moving toward agentic graphs"

"Prompting is basically finished"

In just 10 minutes, she builds her complete Claude Code setup live from an empty terminal

Agents → Loops → Graphs → Self-Improving Systems

Prompting was the old workflow

Graph engineering is the next one

This 10-minute breakdown is worth more than most $1,000 agent engineering courses

Watch it today

Then save the full guide below before everyone catches on ↓

[Google Cloud @googlecloud]

From grounding AI with your own company data to building smart agents and boosting productivity, Stephanie de Albuquerque breaks down the core pillars of the Gemini Enterprise App.

Use our docs to get started building → https://t.co/QXp5AsAlMx

[CyrilXBT @cyrilXBT]

Google just quietly released a free 2‑hour deep dive into full graph engineering—starting with one prompt and scaling all the way to a hundred agents connected through loops and graph structures.

17:44 – Ship your first agent
39:30 – Loop engineering: iterate, validate, stop
1:12:38 – Graph engineering fundamentals
1:34:26 – Self-throttling agents
1:55:05 – The complete graph for multi‑agent systems

Most folks build one agent and call it done. This course walks through the whole machine—where agents don’t just run, they organize themselves into a graph.

Watch it now, then hit the graph engineering playbook below for the deeper teardown.

[Codez @0xCodez]

Anthropic engineer:

"At Anthropic, 90% of our engineers building agentic Loops and Graphs powered by MCP

loops + graphs + MCP - that's how the self-learning agentic system looks like"

in a 25-minutes workshop, the Anthropic engineer who created MCP reveals how to build a self-learning agentic system

Worth more than a $500 agentic course on the internet

Watch the masterclass, then read how to build self-learning agents with MCP in the article below

[Krishna Agrawal @Krishnasagrawal]

Andrej Karpathy’s 1-hour Stanford lecture on AI engineering is one of the best explanations I’ve seen of how AI systems actually work.

The progression is simple:

10% → LLM
30% → Prompt
50% → Agent
70% → Loop
100% → Graph

The key takeaway:

AI engineering isn’t just about writing better prompts.

It’s about building systems around models — giving them context, memory, tools, feedback loops, and data flows.

“Delete everything, keep Graph.”

Definitely worth watching if you’re building with AI agents.

Watch → Bookmark →