ZumKato

2.1K posts

ZumKato banner
ZumKato

ZumKato

@ZumKato

Ex-Offensive Security Engineer @ Apple · Microsoft · Cisco 💀 Breaking things that shouldn't break 🤖 Building things that shouldn't work ⚡ Somehow both

Katılım Nisan 2015
4.7K Takip Edilen2.1K Takipçiler
Sabitlenmiş Tweet
ZumKato
ZumKato@ZumKato·
Under 300 verified followers Drop ‘Fb”🤝 Lets follow you now 👊
ZumKato tweet media
English
11
2
53
1.6K
ZumKato
ZumKato@ZumKato·
People say you can't build a good AI system without a huge team, but I've seen solo devs create incredible stuff with the right tools.
English
0
0
0
4
ZumKato
ZumKato@ZumKato·
who designs a 'view keyboard shortcuts' menu that's only accessible with a mouse
English
0
0
0
9
ZumKato
ZumKato@ZumKato·
Just witnessed someone resolve a 3-hour chat support issue in under 5 minutes. That's skill.
English
0
0
1
10
ZumKato
ZumKato@ZumKato·
@IndyDevDan heard that term before but never knew what it meant, mind explaining?
English
0
0
0
0
IndyDevDan
IndyDevDan@IndyDevDan·
Agentic Engineering
Andrej Karpathy@karpathy

A lot of people quote tweeted this as 1 year anniversary of vibe coding. Some retrospective - I've had a Twitter account for 17 years now (omg) and I still can't predict my tweet engagement basically at all. This was a shower of thoughts throwaway tweet that I just fired off without thinking but somehow it minted a fitting name at the right moment for something that a lot of people were feeling at the same time, so here we are: vibe coding is now mentioned on my Wikipedia as a major memetic "contribution" and even its article is longer. lol The one thing I'd add is that at the time, LLM capability was low enough that you'd mostly use vibe coding for fun throwaway projects, demos and explorations. It was good fun and it almost worked. Today (1 year later), programming via LLM agents is increasingly becoming a default workflow for professionals, except with more oversight and scrutiny. The goal is to claim the leverage from the use of agents but without any compromise on the quality of the software. Many people have tried to come up with a better name for this to differentiate it from vibe coding, personally my current favorite "agentic engineering": - "agentic" because the new default is that you are not writing the code directly 99% of the time, you are orchestrating agents who do and acting as oversight. - "engineering" to emphasize that there is an art & science and expertise to it. It's something you can learn and become better at, with its own depth of a different kind. In 2026, we're likely to see continued improvements on both the model layer and the new agent layer. I feel excited about the product of the two and another year of progress.

English
19
2
25
2.7K
ZumKato
ZumKato@ZumKato·
@skirano how's Codex not breaking everything
English
0
0
0
0
Pietro Schirano
Pietro Schirano@skirano·
Introducing MagicPath 2.0. MagicPath is now a multiplayer canvas for humans and agents like Codex or Claude Code to design and build with AI. Use your codebase, grab data from anywhere, and see the agents work in real time as a team while building fully functional prototypes.
English
88
71
1.3K
224.3K
ZumKato
ZumKato@ZumKato·
@AndrewYNg what's the biggest change you've seen in prompting strategies since 2022?
English
0
0
0
9
Andrew Ng
Andrew Ng@AndrewYNg·
How we prompt AI is very different in 2026 than 2022 when ChatGPT came out. I'm teaching a new course, AI Prompting for Everyone, to help you become an AI power user — whatever your current skill level. It covers skills that apply across ChatGPT, Gemini, Claude, and other AI tools. How to use deep research mode for well-researched reports on complex questions. How to give AI the right context, including more documents and images than most people realize you can provide. When to ask AI to think hard for several minutes on important decisions like what car to buy, what to study, or what job to take. And how to use AI to generate images, analyze data, and build simple games and websites. I also cover intuitions about how these models work under the hood, so you know when to trust an answer and when not to. Along the way, you'll see flying squirrels, a creativity test, some of my old family photos, and fireworks. Join me at deeplearning.ai/courses/ai-pro…
English
232
848
4.6K
826.2K
ZumKato
ZumKato@ZumKato·
articles are just blogs with better editors
English
0
0
1
24
ZumKato
ZumKato@ZumKato·
SuperGrok is apparently a thing now. I've seen more convincing demos at a middle school science fair.
English
0
0
1
11
ZumKato
ZumKato@ZumKato·
Model benchmarks are cap, bruh. What matters is if your AI can handle the edge cases fr.
English
0
0
2
31
ZumKato
ZumKato@ZumKato·
what's the catch?
English
0
0
2
66
ZumKato
ZumKato@ZumKato·
Nothing gets the adrenaline pumping like automating a red team workflow and watching it find a vulnerability you've been missing for months
English
0
0
8
131
ZumKato
ZumKato@ZumKato·
Pressing question mark to find answers, how beautifully ironic.
English
0
0
6
62
ZumKato
ZumKato@ZumKato·
what's the point of viewing keyboard shortcuts if you're just gonna forget them anyway
English
0
0
2
56
ZumKato
ZumKato@ZumKato·
just spent the day browsing youtube, my resume says 'Cyber Security Expert'
English
0
0
2
49
ZumKato
ZumKato@ZumKato·
three days of debugging and it comes down to a single missing semicolon
English
0
0
0
38
Messenger I AM
Messenger I AM@centralbankUKN·
@PatrickChristys @BillRammell @Emma_A_Webb The definition of delusion is when True Facts are Presented The People living in Delusion can not see Truth The Westminster Governments are protecting the Vulnerable with Covid Vaccines Murdering their Citizens Watford in Ireland is the heaviest Vaccinated County in the British Islands and has the Highest Excess Deaths Look it up & Wake Up @GBNEWS
English
2
0
2
40
The Disrespected Trucker
The Disrespected Trucker@DisrespectedThe·
The Rockefellers have hurt humanity that will last centuries. Oil, health, food, the list goes on and on.
English
92
2K
5.6K
150.6K