“You only live once? False. You live every day. You only die once.” - Dwight Shrute
Ho Chi Minh City
Joined April 2009
- Tweets3.2K
- Following1.4K
- Followers363
- Likes2.6K
Denny Nguyen retweeted
I wasn't expecting this today.
Jack Dorsey (the guy who literally created Twitter) released something for FREE that people are losing their minds over.
26.2k stars on GitHub in days.
It's an AI employee that runs your actual business.
Not another chatbot. A real team member that handles work while you sleep.
Here's what blew my mind:
↳ Download it for free (no catch, it's yours)
↳ Set up your own private workspace, everything stays on your server
↳ Drop the AI into your team chat like you're hiring someone new
↳ Control exactly what it can access and do
↳ Your whole team can direct it in real-time
I spent 2 hours testing this and it's not even close to what I expected.
Save this before it gets buried.
Denny Nguyen retweeted
Hot take: I think it's still important to understand the code that our agents write!
In this mega thread (based on my AIE talk today), I will explain why that's the case, and show some ideas for how to efficiently understand code. Alright, let's dive in. 1/
Denny Nguyen retweeted
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 this.
Denny Nguyen retweeted
Ex-Google engineer reveals how to build AI agent loops, harnesses, LLM ops, and evals in 19 minutes.
Trace → evaluate → diagnose → fix → ship → repeat.
That loop is how agents self-improve over time.
Agentic loops + harness + memory + evals - that’s the senior engineer stack.
This is better than $500 paid courses on the same topic, explained in under 20 minutes.
Watch it, then save the framework below.
Denny Nguyen retweeted
you can now teach Codex by demonstration:
Denny Nguyen retweeted
KARPATHY JUST HANDED EVERY DEVELOPER THE EXACT FILE CLAUDE CODE NEEDED FROM DAY ONE.
65 lines. 110K stars. the cheat code for every broken workflow you've been blaming on the model.
if I had this a year ago, I would've shipped twice as fast.
make sure to bookmark it before it gets lost in your feed.
I was losing 2 hours a day to Claude rewriting code I didn't ask it to touch.
then I found CLAUDE. md.
90 seconds to set up. changed everything.
Karpathy identified 4 failure patterns Claude Code repeats constantly, in his own words:
→ silent assumptions: Claude makes decisions without checking with you
→ code bloat: 1000 lines written when 100 would do
→ collateral damage: Claude edits code unrelated to the task
→ no success criteria: Claude loops with no finish line
these aren't model failures. they're missing instructions.
CLAUDE. md gives Claude the 4 rules it needed from day one:
→ think before coding, state assumptions. ask before assuming.
→ simplicity first, minimum code. nothing speculative.
→ surgical changes, touch only what is required. nothing adjacent.
→ goal-driven execution, define success before starting. loop until verified.
65 lines. no build step. no framework. no dependencies.
just the 4 principles every developer already knew, but needed Karpathy to write down.
ClaudeKit is the only team you need to build something like this (theclaudekit.com)
the guide on how to learn Claude below (every resource you need)
xitter.cf/humzaakhalid/status/20…
Denny Nguyen retweeted
Claude Code can now upload and edit HTML artifacts that you can share with your team or other Claudes!
Starting with teams so you can share internally with your team, coming to Pro and MAX plans soon!
Denny Nguyen retweeted
what is agent looping
for the last two years we prompted agents one task at a time. that is starting to change
instead of asking an agent to build the landing page and then driving every step yourself, you set up a loop that handles discovery, planning, the work, checking, and iterating until the goal is met
looping is a setup you build. almost any agent harness can run it, it just depends on how you wire it up
at its simplest, looping is one agent working on itself:
> researches
> drafts
> checks the draft against a goal
> fixes what is weak
> runs that cycle again until the work clears the requirements
you are not prompting each step anymore. the agent repeats the cycle for you
the bigger version is a fleet looping. you give an orchestrator agent a goal, it breaks the goal into pieces, hands each piece to a specialist agent, and those specialists hand smaller jobs to their own subagents
the whole tree keeps looping through discovery, planning, execution, and verification until the goal is met
one agent looping is like a person redoing their own draft. a fleet looping is a whole team running a project end-to-end
you create a goal, and the system runs the loop until it finishes within the reqs you set
open and closed looping:
OPEN LOOPING is exploratory. it still has conditions and a goal, but you give the agent or the fleet a wide space to move in. it can try different paths, discover things, build something you did not fully spec out
this is the exciting end, it is what Peter and others are doing, and tbh it is where I want to spend more time
the catch is cost, an open loop with real room to explore burns an insane amount of tokens. for the 90 percent of people without an unlimited budget it is not runnable yet, and pointed at projects with a loose standard it turns into a slop machine
CLOSED LOOPING is bounded. a human designs the end-to-end path first:
> clear goal
> defined steps
> an eval at each step
> a point where it stops or hands back to you (and feeds back performance data)
the agents still loop, but inside framework you built. it gets better every run because each pass feeds the next, and it runs on a normal budget because the path is tight.
for most marketing work, closed is the one that pays off today.
> the orchestrator owns the goal
> the specialists own the steps
> the subagents do the narrow work
> an eval gate make sure its not slop
Denny Nguyen retweeted
AI coding agents can now extract any website's design system directly from the terminal.
I love small projects like this that Hyperbrowser creates. Their repo is full of them.
🤝 Paid partnership
Add the /design command
→ mkdir .claude/skills/design
→ Drop in SKILL. md
→ Restart Claude Code
Get SKILL. md from:
github.com/hyperbrowserai/ex…
Denny Nguyen retweeted
Folks: when you write skills, ask your agent to be token efficient, relax grammer. I see too many skills that write books in the skill description, and all that crap is loaded into every context.
I wrote a skill that finds the worst offenders. github.com/steipete/agent-sc…
Denny Nguyen retweeted
Anthropic just paid millions to hire Andrej Karpathy.
He gave you the same knowledge for $0 the same week.
Co-founder of OpenAI. Former head of AI at Tesla. The man who coined vibe coding.
No recruitment fee. No exclusive access. Just a link and 29 minutes.
LLMs are ghosts not animals.
Vibe coding is dead.
Software 3.0 is here.
Watch it.
Then read this.
Because Karpathy tells you what Software 3.0 is.
This shows you how to build one - a software factory with Claude Code that ships features while you sleep.
The full build guide is below.
Denny Nguyen retweeted
karpathy's CLAUDE.md hit #1 on github trending.
220,000 stars. most devs still haven't read it.
it's 65 lines.
it took AI coding accuracy from 65% to 94%.
the 4 rules inside:
→ think before coding
state your assumptions. ask when unsure. never guess.
→ simplicity first
write the minimum code that solves the problem.
no abstractions nobody asked for.
→ surgical changes
don't touch code unrelated to the request.
every changed line must trace back to what was asked.
→ goal-driven execution
turn vague instructions into verifiable success criteria
before writing a single line.
that's it.
65 lines. 4 rules. 94% accuracy.
save this before everyone else does.
Denny Nguyen retweeted
Boris Cherny, the creator of Claude Code at Anthropic, just explained how to write prompts that actually work
CLAUDE.md files, memory shortcuts, parallel sessions, and prompting patterns all in one video and completely free
SpaceXAI just signed a major compute partnership with Anthropic, giving the Claude maker access to Colossus 1, one of the world's largest and fastest-deployed AI supercomputers.
Colossus 1 features over 220,000 NVIDIA GPUs including dense deployments of H100, H200, and the next-generation GB200 accelerators.
Anthropic plans to use the additional compute to directly improve capacity for Claude Pro and Claude Max subscribers, the heavy users who have been hitting rate limits as the AI race accelerates.
The bigger story is in the second part of the announcement.
Anthropic also expressed interest in partnering with SpaceX to develop multiple gigawatts of orbital AI compute capacity.
What this means: AI data centers in space.
Elon's bet on space-based compute is starting to look prophetic.
The compute needed to train and run frontier AI is already outpacing what Earth's power grids, land, and cooling can deliver on the timelines that matter.
SpaceX is the only company with the launch cadence, mass-to-orbit economics, and constellation operations experience to make orbital data centers a near-term engineering project rather than a science fiction concept.
Anthropic just publicly endorsed that thesis with their checkbook and a partnership announcement.
Two of the most consequential AI labs in the world are now actively planning to build infrastructure in low Earth orbit.
Denny Nguyen retweeted
ANTHROPIC JUST KILLED THE DEMO AGENT ERA.
Their Agents team showed exactly what production grade looks like.
Not theory. Not a tutorial. A four layer framework for multi agent systems built to actually work in the real world.
30 minutes.
This is the video I wish existed 6 months ago.
Denny Nguyen retweeted
GitHub has just solved the biggest problem with vibe coding.
They just dropped Spec Kit and it exploded to 95K+ stars within days.
The reason is simple:
Most AI coding agents jump straight into writing code before actually understanding the project.
That’s why you get random architecture decisions, broken flows, inconsistent files, and hours wasted debugging things you never asked for.
Spec Kit changes the workflow completely.
Instead of coding first…
the AI is forced to think first.
It creates a full project specification before touching a single file.
So the agent understands:
* what you're building
* the constraints
* missing details
* architecture decisions
* implementation order
before execution even starts.
The workflow looks like this:
→ /constitution = coding rules + standards
→ /specify = define the product
→ /clarify = resolve ambiguities
→ /plan = architecture + tech stack
→ /tasks = execution breakdown
→ /implement = build phase
Result?
Far fewer hallucinations.
Cleaner codebases.
More reliable outputs.
Way better collaboration between humans and AI agents.
Works with:
Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, and 25+ other agents.
Open source.
95K+ stars.
8K+ forks.
Built by GitHub.
Repository 👇
github.com/github/spec-kit
Denny Nguyen retweeted
RAG vs. CAG, clearly explained!
RAG is great, but it has a major problem:
Every query hits the vector DB. Even for static information that hasn't changed in months.
This is expensive, slow, and unnecessary.
Cache-Augmented Generation (CAG) addresses this issue by enabling the model to "remember" static information directly in its key-value (KV) memory.
In fact, you can combine RAG and CAG for the best of both worlds.
Here's how it works:
RAG + CAG splits your knowledge into two layers:
↳ Static data (policies, documentation) gets cached once in the model's KV memory
↳ Dynamic data (recent updates, live documents) gets fetched via retrieval
This gives faster inference, lower costs, and less redundancy.
The trick is being selective about what you cache.
Only cache static, high-value knowledge that rarely changes. If you cache everything, you'll hit context limits. Separating "cold" (cacheable) and "hot" (retrievable) data keeps this system reliable.
You can start today. OpenAI and Anthropic already support prompt caching in their APIs.
I have shared my recent article on prompt caching below if you want to dive deeper.
Have you tried CAG in production yet?
Below, I have quoted an article that I wrote on prompt cashing and how Claude Code achieves a 92% cache hit-rate. Give it a read.
Denny Nguyen retweeted
Spotify's Chief Architect just showed how they ship 4,5K deployments /day with Claude at Anthropic stage
27-minutes. free. By #1 music app dev
"More than 99% of our engineers use AI coding tools. Adoption took off after Opus 4.5"
Worth more than any $500 vibe-coding course.
Creator of Claude Code just dropped a 6-min workshop on new Claude feature during live session in London.
Boris Cherny: “A lot of my code these days is written by "routines". I’m not doing the prompting - I create the routines that do the prompting.”
6 minutes. Free. From a live session.
Watch this now. This will change the way you vibe-code forever.