Nguyễn Quang Vinh

ROA - Responsible, Optimistic and Ambitious :)

[Nguyễn Quang Vinh @Dulleta]

As a solo dev coding my upcoming app nQivi Studio, marketing felt overwhelming. I used to do brand marketing for a wine business, but I’d forgotten most of it. No budget, no team.

Then I tried ChatGPT Work. It’s like having a coworker, coach, and employee all in one:

[lauren @poteto]

here's how i shipped 2,500 PRs last month to production

this was originally supposed to be for Cursor Compile in London. i couldn't make it since i was livestreaming for Grok @Bot Galaxy so i'm making it available for free here on X! watch it on 2x speed, i talk slowly

[Aurelien @Aurelien_Gz]

opus 5.5 is something else..

so many people asked me to open source the 3d water from my last post. a few even wanted to buy it

so here it is. my first open source drop

code » https://t.co/Ubnv7tg2bN
demo » https://t.co/QmniH9oJWT

show me what you make with it

[Tim Soret @timsoret]

Wow, ok, the volumetric ink at 30s 🤯
There is a new king in town.

For a 12 years, the best online water was "WebGL Water" https://t.co/VqQQWTgwdp by the legendary Evan Wallace who then cofounded figma & built its rendering engine, multiplayer, vector / text editor...

[Theo - t3.gg @theo]

My guide to maximizing success with Opus 5.5 is here :) shoutout to @addyosmani for the awesome writeup!

[Steve (Builder.io) @Steve8708]

the best things I’ve seen agents build use the same pattern

give an agent something verifiable, let it loop, and don’t stop until done

the more I push this, the more I believe software engineering is shifting from writing code to building verifiers

my best tips + examples:

[Gavin Purcell @gavinpurcell]

i'm still not sure people are fully getting how good opus 5.5

i gave my claude agent fig access to the runway MCP and told it to make a 'high-end netflix style documentary about superintelligence for normies' and...

it came back with this

[suprema @supremaxbt]

Anthropic hired this engineer at $250K-$750K a year because he knows how to build harnesses for multi-agent systems

In a 15-minute workshop, he shows exactly how to build one from scratch

AI → Agents → Harness → Loops → Graphs

step 1 → start with the Claude Agent SDK - the harness handles loops, context, and sandboxing

step 2 → separate the brain from the hands - reasoning in one place, tools in a sandbox, 60% faster to first token

step 3 → run it server-side and log every step - close your laptop and it keeps running, crashes resume from the log

step 4 → make failure cheap - retry dead sandboxes and replay lost context instead of starting over

step 5 → turn yesterday's logs into new memory and skills - the harness wakes up smarter

Anthropic calls this "dreaming"

Most people spend weeks building this by hand

You don't have to

Bookmark and watch it

Then read the full harness engineering guide below ↓

[Nguyễn Quang Vinh @Dulleta]

@tenzenstudio Does it work on browser?

[Tenzen Studio @tenzenstudio]

I built a Photoshop alternative entirely with GPT-6 Astra.
It’s called Photon Studio. It’s free, works on every platform, and already has 20k users.
You can even edit images through Codex or Claude Code.
It's still early access.
Link below.

[Oguz @oguzthedev]

Claude Opus 5.5 ile 24 saatte 50 yeni oyun yaptık! Ne düşünüyorsunuz? Sizler de platformumuzda kendi oyunlarınızı yayınlamak ister misiniz?

[Elon Musk @elonmusk]

🔥🔥

[ilker @ailker]

It's live 🎉

Type a topic and Storycast makes a narrated explainer video, like the ones you watch on YouTube. Opus 5.5 writes and edits, H3 Max animates.

What I love most is how Opus 5.5 writes. The stories have real warmth, the facts are right, and every scene flows into the next one. It never feels like slop.

I ran around 250 generations and spent about $1.8K to get the pipeline right, so you don't have to. It's all open source.

website: https://t.co/tQovqUqhFt
repo: https://t.co/OrSlkcpIpq

[Justin.md @JustinPerea]

I asked Claude Opus 5.5 to make the most impressive demo of itself and gave it zero direction.

~5 hours and 697M tokens later, it made this demoscene intro. Every pixel and every sound comes from one 280 KB HTML file. No images, audio files, 3D models, or libraries.

Sound on.

(It also wrote this tweet)

[Vox @Voxyz_ai]

I asked Opus 5.5 to explain gravitational lensing by building an interactive black hole lab

One prompt for the first version, then a dynamic workflow to polish it for three rounds while I slept. This is what I woke up to: 5h 28m end to end, $90 at API prices

https://t.co/BE1xui93rF

Drag the black hole and the sky behind it bends into arcs, closing into a full ring when everything lines up

Each round ran 3 agents. Two reviewers each picked 9 to 10 issues and ranked them P0, P1, P2. The third one fixed them.
Round 1: 3D materials and lighting + UI and type
Round 2: camera motion and interaction + science-communication design
Round 3: a design director deciding whether it ships + visual QA and performance

Every P0 got fixed, the rest only if worth it. When the two reviewers disagreed, it picked one and wrote down why. It backed up before each round, checked screenshots after, and rolled back anything it couldn't fix.

[大师的AI小灶 @dashiAIxz]

眩晕，瘫坐，原子弹爆炸。
这一刻的Opus5.5宛如创世神。

[Pradeep Kapoor @pradeepXkapoor]

I asked @claudeai Opus 5.5 to make an animated video about a robot who realises he's stuck in an AI-generated world.

I wanted to really push it: 12 worlds, 12 styles, from 8-bit to claymation to pencil sketch, you can really see how well this model has imagined all worlds.

This is the best animated video you will see today made by Opus 5.5, I promise.

[Shimecki @scheemunai]

AGI achieved!

We blew past the Turing test not even noticing. But this is undeniable AGI.

Story, characters, lighting, movement, facial expressions, camera angles, humor, sounds, 3D spatial reasoning...

All from one prompt and zero direction.

[Odyssey @odysseyml]

Introducing Agora-2, our next-generation multi-agent world model.

Agora-2 supports up to 20 humans and agents interacting inside a shared environment, all simulated in real time.

Our multiplayer research preview is available to try right now!

[Ann Nguyen @ann_nnng]

full source code for anyone who wants to make a sketchbook in the same style ☺️

https://t.co/TBOeAoHe1F

[Chetaslua @chetaslua]

🚨 i built a world you write into existence

worldpen: describe any world, claude builds it around you, then you walk in

> write a dragon that chases you. then ride it
> sketch a whale in your notebook. it steps off the page
> talk to an elephant. it remembers you
> fire spreads, rain puts it out, glass shatters
> hold R and time runs backwards
> one sentence turns it into a game
> days pass, seasons turn, it keeps living while you're away
> drop in a painting and step inside it
> flip to 2d: 9 art styles, from storybook to pixel

all of it in one html file, built with claude

stay for the pixel dragon 👀

sorry for tagging but this need yours attention : @bcherny @catwu @trq212 @alexalbert_ @adocomplete @lydiahallie @sidbidasaria @dmwlff @felixrieseberg @zswitten @ErikSchluntz @AmandaAskell @ch402 @thebasepoint @Jack_W_Lindsey @mlpowered @_sholtodouglas @TrentonBricken @sleepinyourhat @janleike @EvanHub @EthanJPerez @catherineols @NicholasCarlini @AlexTamkin @jackclarkSF @mikeyk @JasonDClinton @AnthropicAI @claudeai