Tirth Bal retweeted
Diwali theme is coming to Haikuvibe. It's adorable
play.google.com/store/apps/d…
Tirth Bal retweeted
Urgent looking for a flatmate or two
Found a pretty cool 2bhk and a 3bhk but need flatmates
Rent 40k / 60k
Close to indiranagar
Non smokers only
DM lol
I want to move in asap
Replying to @delhivery
@Delhivery My father’s medicine order from Apollo has been stuck in Jaipur since October 19, yet it’s still not delivered! It’s MEDICINE, not a luxury parcel.
Why the repeated delays? If you can’t deliver on time, why accept shipments? Please resolve this urgently!
Tirth Bal retweeted
Cloak Proxy is a free, native Mac app that shows every request your Mac and phone make.
Decrypt HTTPS, pause and edit requests, mock responses, see what each LLM call costs, and let Claude drive it over MCP (148 tools).
No account. Free for good.
subcloak.com/apps/cloak-prox…
Tirth Bal retweeted
🚨 What can we learn from real-world AI security failures?
We have seen AI agents delete production databases, prompt injection attacks expose sensitive information, and vulnerabilities put AI-powered applications at risk.
But reading about an attack and understanding how it actually works are two different things.
🚀 Today, I'm launching the 𝗔𝗜 𝗦𝗲𝗰𝘂𝗿𝗶𝘁𝘆 𝗜𝗻𝗰𝗶𝗱𝗲𝗻𝘁 𝗗𝗮𝘁𝗮𝗯𝗮𝘀𝗲 on GenAI Security Lab.
🔎 What's inside?
🔹 Real-world AI security incidents and vulnerabilities
🔹 Technical breakdowns of how attacks work
🔹 Root causes and lessons for developers and security professionals
🔹 Mitigation strategies to help prevent similar attacks
🔹 Links to hands-on labs where you can practise the underlying attack techniques.
The idea is simple: connect real-world AI security incidents with practical, hands-on learning.
Instead of just reading about prompt injection, AI agent vulnerabilities, data leaks, or MCP security issues, you can explore the technical details and practice relevant attack techniques in hands-on labs.
Whether you're an application security engineer, penetration tester, developer, or AI security researcher, this resource is built to help you go beyond theory.
🔗 genaisecuritylab.com/inciden…
This is part of my ongoing work on GenAI Security Lab, where were building hands-on labs to help security professionals learn to test and secure LLMs, RAG applications, AI agents, and MCP integrations.
Which real-world AI security incident should we break down next?
#AISecurity #LLMSecurity #CyberSecurity #AppSec #GenAI
Tirth Bal retweeted
I work on Distributed systems so naturally my interests are all over the place 👋
Hey I am Kv/Kai - an engineer working on Distributed systems and Databases, and someone who finds himself asking "but how does it actually work?" a lot.
Asking that question has led me to create 150+ technical podcast episodes and tutorials. Kafka, database internals, the JVM, streaming systems, engineering and AI.. plenty of rabbit holes with great company of experts along the way.
I refactored my website to help you easily find the right rabbit hole for you. Something I chose to call "Knowledge Atlas"
Give me a follow and have a look at the website to find some great episodes on the channel aligning with your interest.
Feel free to comment and introduce yourself so I can follow you back!
Cheers,
Kv
I am hiring Staff Backend and Web engineers for our international team (based in Bangalore). You'll work with a high-energy team and leaders to take JioHotstar's tech stack global.
Sample JD: lnkd.in/gbhsKUQQ
Please send your resume to international@jeet.world
LLMs write text. Jev returns decisions.
In this video I explain how an LLM answers, how TypeSafe's Jev model answers, the difference, and a real use case (invoice triage with confidence gating).
youtu.be/IA0o1F5KG9s
Built Ask Jev, a magic 8-ball that decides your future.
You type a question.
Jev reads your horoscope for today and makes the call 🔮
Link: 8-ball-jev.vercel.app/
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?
I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev
• 20-200x faster
• 40-400x cheaper (w/ output tokens free)
• Frontier composable intelligence optimized for decisions
AFAICT the shortest path to AI-based economic revolution
Tirth Bal retweeted
Ever since the AI/LLM wave hit, I've been keeping a scrappy little personal list — the payloads and techniques I actually reach for when testing AI apps. My own private cheat sheet, basically.
And lately, so many of us keep hearing the same question from clients: "Can you security-test the AI part too?" Honestly? Most folks I've talked to didn't have a solid methodology for it yet. No judgment — this space is moving at light speed, and we've all been figuring it out as we go.
So today I'm genuinely excited to finally share mine: the AI Security Testing Cheat Sheet, part of the @genaiseclab project.
Here's what's inside:
🔍 150+ practical techniques across 20 sections — all mapped to the OWASP LLM Top 10 2026
💉 Prompt injection, indirect & multimodal injection, sensitive data disclosure, tool and agent abuse, MCP attacks
📝 Real example payloads for every technique
📋 A tracker you fill in as you test, plus findings export and reporting templates
And the best part — it's truly free. No signup, no credit card, no gate. Just grab it and go. ❤️
This is a living project, too. If there's a technique you think I've missed, I'd genuinely love to hear it — drop a comment or DM me and I'll fold it in. This thing gets better when we build it together.
👉 genaisecuritylab.com/cheatsh…
If it saves you even a few hours on your next assessment, that honestly makes my week. And feedback — good or bad is welcome, so tell me what you think! 🙏
Tirth Bal retweeted
Better if in a Gated Premium Society. And furnished/semi-furnished to an extent.
Looking within 5-8km radius of office, the near the better
💵 Rent Budget: 25-30K / month ( no problem with brokerage )
Please DM if you're looking for a flatmate & has with similar requirements.
Tirth Bal retweeted
I spent years breaking systems for a living, and the only thing that ever made me better was doing it — never reading about it. AI security is about to be part of every security job, not a specialty, so I built the hands-on AI security training I always wanted. It's live today 👇
Launch week: 25% off everything with code LAUNCH25OFF — individual plans, team seats, and the certification (offer expires 10th September 2026). Community labs stay free.
Nobody got good at web security by reading about SQL injection.
You got good by breaking things, then fixing them.
AI security is becoming that same baseline skill — the one every pentester, AppSec engineer, and developer shipping AI features is about to be expected to have. And almost all the training for it is passive: a slide deck and a multiple-choice quiz.
So we built the opposite.
GenAI Security Lab: 200+ live, deliberately vulnerable AI targets running on real models. LLM chat apps, MCP servers, RAG pipelines, tool-using agents. One attack technique per target.
Nobody reads a wall of text, so we didn't write one. Each OWASP topic is a guided path, not a PDF — a few-minute concept video, a diagram of exactly where the trust boundary breaks, the real incident behind it, and predict-before-reveal checkpoints that make you commit before you ever touch the target.
Then you run the loop: Attack → Defend → Verify. Exploit it for real, implement the fix, verify it holds — across two tracks per topic, offensive and defensive.
It's a live system you break with your own hands, then close the hole you found. Not a module you click through.
Why it's built this way: I've spent years as a top bug bounty hunter and a decade in security consulting. The only thing that ever made me better was breaking real systems. This is the training I wanted when I started on AI.
It's live today. Community labs are free — no credit card:
genaisecuritylab.com
Running a team? Per-seat plans, one methodology across every engineer, and completion records that mean something — because your people earned them on live targets, not a webinar sign-in.
🎉 Introducing: Folio - Duolingo for books
Turn the books you already own into a game you’ll actually want to keep playing, and build a lasting reading habit.
More features coming this week.
Link below 👇🏻
#Shipathon #BuildInPublic
Tirth Bal retweeted
We are soon launching the Child Beggar-Free Delhi Campaign across all 13 districts to protect children found begging and secure their future.
Children will not be moved by force. With DCPCR and NGOs, we will counsel families, address their difficulties and provide better alternatives. The campaign will also identify and expose organised gangs forcing children into begging.
Have a suggestion? Comment or DM us.
#ViksitDelhi
Tirth Bal retweeted
I missed reading the newspaper, so I built one to keep me caught up with all things AI and engineering :)
Every day there is more AI, database, and engineering news than anyone can keep up with. I used to follow a series of steps, and now, I have turned it into a simple website tdd.cat - It holds the most interesting stories across AI, databases, and engineering in one place.
Every story is pulled from arXiv and Hacker News, then ranked based on how interesting and useful I find it. It is slightly tuned to my taste, so if you enjoy what I usually post, you will enjoy this curation as well.
By the way, you can also filter by source (arXiv or Hacker News) and signal level (a combination of interestingness and helpfulness). On busy days, you can jump straight to stories marked Notable, Recommended, Must-Read, or Essential.
I want this to be the tab that stays open on one monitor. Your agents run their tasks on one side, and you catch up on what matters on the other :)
No feed to scroll. Just stuff worth knowing.
Hope this helps.
Tirth Bal retweeted
We want to see 100+ more HackerFabs
“How to build your own HackerFab” - we are organising a webinar tomorrow, 28th June, 5pm on GMeet - will cover everything that’s needed- and follow up with a QnA.
It’s much easier than it sounds and every college should have one!
Link below


























