Hung Vinh (@hungv47) header
Hung Vinh (@hungv47) profile picture

so cool things & get paid for it // GTM & Growth // $300k ARR side hustle

Joined August 2015
Photo by Hung Vinh (@hungv47)Photo by Hung Vinh (@hungv47)Photo by Hung Vinh (@hungv47)Photo by Hung Vinh (@hungv47)Photo by Hung Vinh (@hungv47)Photo by Hung Vinh (@hungv47)Photo by Hung Vinh (@hungv47)Photo by Hung Vinh (@hungv47)Photo by Hung Vinh (@hungv47)Photo by Hung Vinh (@hungv47)
Marketing Engineering Explained Low IQ: Find the one repetitive thing eating hours. Write a script with a thinking loop connected to a live data stream. Only burn tokens where needed, everything else is CPU Midwit: An agent org chart: an orchestrator "CMO agent" delegating to an SEO agent, a paid agent, a content agent, and a social agent. Hub and spoke. Drawn in Excalidraw before a single thing runs. Building the internal agent platform first — registry, routing layer, prompt management system, observability framework — when three agents exist 14-step chains where step 6 is an LLM deciding which branch to take, and no step is idempotent Write access to live channels on day one: publishing, sending, changing budgets Prompt engineering treated as the core craft: 4,000-token system prompts, "You are a world-class CMO with 20 years of experience," a versioned few-shot library Framework churn — LangChain, then LangGraph, then CrewAI, then custom. Three rewrites, zero agents in production. RAG over the entire company Notion so the agent "has context" Eval theater: an LLM judge scoring outputs 1–10, averaging 8.4, never once compared to a human label A vector DB and a memory layer for an agent that runs daily over 40 rows $2K/month in tokens generating content nobody publishes KPIs: agents deployed, tasks automated, "hours saved" No drift detection — so the SEO agent has been writing about the wrong product for three weeks and publishing it Nobody on the marketing team can run, change, or debug any of it without you High IQ: One agent, one job, narrow scope. Deterministic code everywhere the task is deterministic; the model only where the input is genuinely unstructured. A human at every irreversible action until the error rate earns autonomy. A drift check that runs every morning. Build software that runs marketing systems.
15
5
2
40
7,246
u need only a single mcp and that's executor .sh where the rest of your mcps are connected if u have a better solution i'm all ears
23
3
1
110
19,212
Hung Vinh retweeted
the fact that job postings now say "growth engineer" instead of "marketing manager" tells u everything about where its headed distribution is becoming an engineering problem the ppl who figured this out early are printing rn
26
15
7
416
28,072
Hung Vinh retweeted
"hard questions are great but only if we deem you worthy enough to not silently downgrade you, or even get access at all"
442
243
138
7,285
762,853
Hung Vinh retweeted
who needs an MCP when you can just let your agent call the API get your agent connected to google search console with executor.sh
Hey @Google can you ship an MCP for the Search Console? Thanks
33
18
1
614
94,396
The computer is being reinvented in the agentic era: - The model is the new CPU. - The harness is the new OS. - Hallucinations are the new bugs. - The context window is the new RAM. - Skills are the new apps. - Markdown files are the new config. - Evals are the new QA. - Context is the new moat. - Permissions are the new firewall - Trust is the new bottleneck. - Prompt is the new programming language - Agent is the new software. Anything you dream of, you can build. This is the greatest time ever to be building with computers.
226
494
66
3,394
205,921
Hung Vinh retweeted
I'll keep becoming more
5
625
18
2,581
46,450
Hung Vinh retweeted
Replying to @LexnLin
For those who are asking: - How to generate media (images, videos) with Claude? ai-cli by @ctatedev - How to animate stuff? Lottie by @konstipaulus - How to generate nice graphics? @paper plugin - How to wire them all into nice animated videos? @HyperFrames_ They are all free
1
1
13
764
Hung Vinh retweeted
Building a product today only testing it via the browser & not via an agent is like developing only for desktop and not checking on a phone during the mobile revolution I’m guilty of this also, it’s a really easy trap to fall into but agents are how people use products now
6
6
2
119
16,728
Hung Vinh retweeted
Introducing the MATLAB Agentic Toolkit Get started 👉 spr.ly/6019BBw4zH
76
382
163
3,571
891,422
Hello! Today we're releasing Paper Desktop Paper is now a canvas for Cursor, Claude Code, Codex. Any agent can read and write html to Paper. • push or pull from your codebase • pull real data from anywhere • less work, more design What will you ship? Sound on 🎶
353
386
177
5,858
2,399,704
Replying to @drewjwiberg
nah the ralph thing is the silliest thing of the year
28
12
6
421
34,151
I've never felt this much behind as a programmer. The profession is being dramatically refactored as the bits contributed by the programmer are increasingly sparse and between. I have a sense that I could be 10X more powerful if I just properly string together what has become available over the last ~year and a failure to claim the boost feels decidedly like skill issue. There's a new programmable layer of abstraction to master (in addition to the usual layers below) involving agents, subagents, their prompts, contexts, memory, modes, permissions, tools, plugins, skills, hooks, MCP, LSP, slash commands, workflows, IDE integrations, and a need to build an all-encompassing mental model for strengths and pitfalls of fundamentally stochastic, fallible, unintelligible and changing entities suddenly intermingled with what used to be good old fashioned engineering. Clearly some powerful alien tool was handed around except it comes with no manual and everyone has to figure out how to hold it and operate it, while the resulting magnitude 9 earthquake is rocking the profession. Roll up your sleeves to not fall behind.
2,554
7,301
2,906
55,188
17,111,890
Here are my Opus 4.5 thoughts after ~2 weeks of use. First some general thoughts, then some practical stuff. --- THE BIG PICTURE --- THE UNLOCK FOR AGENTS It's clear to anyone who's used Opus 4.5 that AI progress isn't slowing down. I'm surprised more people aren't treating this as a major moment. I suspect getting released right before Thanksgiving combined with everyone at NeurIPS this week has delayed discourse on it by 2 weeks. But this is the best model for both code and for agents, and it's not close. The analogy has been made that this is another 3.5 Sonnet moment, and I agree. But what does that mean? Every few generations we get a major model unlock - a moment that unlocks a new way of working. GPT-4 was the unlock for chat, Sonnet 3.5 was the unlock for code, and now Opus 4.5 is the unlock for agents. Thanks to Opus 4.5, agents can now work reliably on increasingly longer time horizons and get real-world work done on your behalf. Opus 4.5 is like a Waymo. You tell it "take me from A to B", and it takes you there. After a few of these experiences your brain realizes "oh. ok. we live in this world now". And then you're hooked. From that moment on, you'll never work the same way again. THE YEAR OF AGENTS 2025 has been touted as the year of agents, and Opus 4.5 + Claude Agent SDK is the pairing that makes that phrase true. The Claude Agent SDK is the best open secret in AI right now. An agent's harness matters almost as much as its model. If you have a bad harness, then you may as well have a bad model. With the SDK you get a world-class agentic harness out-of-the-box which you can now pair with Opus 4.5 to build real-world agents that actually work. I'm reminded of Alan Kay's quote "People who are really serious about software should make their own hardware". The agent version of this is "people who are serious about models should make their own harness". Anthropic clearly believes this, and it's working. The pairing of these tools is magic. I would describe myself as being "unhobblings-pilled", and the Claude Agent SDK + Opus 4.5 is the next major unhobbling. There's now another OOM of new latent economic value stuck in this combo, and it's the job of builders to get it out. If you were bearish on agents, now is the time to turn bullish. "ALL OF THIS IS REAL" "You know what's crazy? That all of this is real". This was Ilya's opening line about the state of AI in his Dwarkesh interview, and I echo that sentiment. I can't believe that Opus 4.5 is real. There have been several times as Opus 4.5's been working where I've quite literally leaned back in my chair and given an audible laugh over how wild it is that we live in a world where it exists and where agents are this good. Nat Friedman has this great question on his website: "Where do you get your dopamine?" Increasingly, I get mine from Claude. LONG ANTHROPIC I saw a post yesterday where someone said that Opus 4.5 was the most important thing to happen to them in their professional career. This will be true for more people going forward. Every year for the past 3 years, Anthropic has grown revenue by 10x. $1M to $100M in 2023, $100M to $1B in 2024, and $1B to $10B in 2025. In Dario's recent DealBook interview he expressed that he wasn't sure if that 10x pattern would hold for 2026. While he's probably right, I do expect Anthropic's revenue at the end of next year to be much higher than everyone expects. It wouldn't surprise me if they passed OpenAI in valuation by early 2027. Opus 4.5 is too good of a model, Claude Agent SDK is too good of a harness, and their focus on the enterprise is too obviously correct. Claude Opus 4.5 is a winner. And Anthropic will keep winning.
170
265
115
3,095
1,476,332
Hung Vinh retweeted
I love entrepreneurship because it allows you to apply anything you learn. At school, you’re told what to learn. At a job, you’re told what to work on, and you only learn until you are good enough to do the job (unless you self-educate out of genuine interest, but being honest, an abysmally low amount of people do that, because those who do realize that in order to learn they must grow, and you can’t grow in someone else’s box). When you do your own thing, the only way to survive is to do something you’ve never done before, which requires you to learn what can’t be taught in school.
165
76
14
1,033
63,705
Hung Vinh retweeted
"I, and I alone, am responsible for everything I think and feel." @naval
152
1,101
43
8,481
348,230
Hung Vinh retweeted
My daily reminder
350
9,593
1,375
69,687
10,820,724
6
15
3
146
16,091
Hung Vinh retweeted
The Neuroscience of Creating New Habits:
17
1,084
20
7,756
1,438,609