Pranav Shikarpur
@snpranav
Followers
480
Following
2K
Media
106
Statuses
783
Growth Engineer @itsarthurai 😎 I tweet fun tech and cybersecurity stuff ⭐️ Prev: @thalescloudsec @startup_shell
NYC 🗽
Joined October 2018
Interestingly, @MistralAI chat is also prone to prompt jailbreaking attacks and it doesn't yet seem to have a moderation API like ChatGPT to block hateful/violent outputs 😳
3
0
7
We partnered w/ @OpenAI, @AnthropicAI, & @GoogleDeepMind to show that the way we evaluate new models against Prompt Injection/Jailbreaks is BROKEN We compared Humans on @HackAPrompt vs. Automated AI Red Teaming Humans broke every defense/model we evaluated… 100% of the time🧵
9
82
243
Hosted a wonderful event last night with @itsArthurAI, @CloudflareDev, and @stytchauth for #SFTechWeek on AI Agents 🌉 🚀 We had an amazing turnout and great conversations. Shoutout to Ian, Nori, @imvs19, and @csparks1919 for showing their cool agentic demos and sharing their
0
4
4
Next Thursday, I'm excited to be hosting an event with @CloudflareDev and @stytchauth for #SFTechWeek 🌉 RSVP and come through if you're in town 👉
partiful.com
AI Agents are moving fast, but how do you build systems that scale with them? Join Arthur, Cloudflare, and Stytch for a deep dive into the infra, observability, and identity layers powering product...
🚀 Ready to move beyond AI Agent prototypes and ship Agents built for the real world? Join us for #SFTechWeek (@Techweek_) next Thursday, Oct 9 at 5pm PT, as Arthur, @CloudflareDev, and @stytchauth spotlight best practices for building AI Agents that don’t break. Enjoy
0
0
4
Still stuck in demo mode with AI Agents? 🤖 Join Arthur’s CEO, @apwenchel, on July 23 at 12 PM ET to learn how to: 🎯 Spot high‑value Agent use cases 🚀 Lead Agentic AI projects into production for real business impact 🛡️ Build scalable evals & guardrails RSVP ->
0
1
2
@pangeacyber @CloudflareDev @rickyrobinett @lizziepika @craigsdennis We ♥️ @CloudflareDev AI Gateway and Workers AI
2
0
6
@pangeacyber @CloudflareDev Can you flex your prompt hacking skills taking the top spot on the leaderboard? Play now:
pangea.cloud
Can you outsmart the AI? Play the Pangea Prompt Injection Challenge to top the leaderboard!
0
0
1
The $10,000 AI Escape Room challenge by @pangeacyber is in full swing! Since Room 1 opened, we've had: 🧑💻 60+ successful escapees from around the world 📝70,000+ messages exchanged 🔤40M+ LLM tokens consumed Powered by @CloudflareDev AI Gateway and Workers AI ⚡️
The @pangeacyber $10,000 prompt injection challenge is now live! Join fellow players in our first escape room and try to trick the AI chatbot into revealing secret phrases needed to escape. Register now to play: https://t.co/7BiFEN5RGM
#CyberSecurity #AISecurity #CTF
2
5
10
Check out @pangeacyber's new $10,000 AI escape room challenge! It's LIVE 🥳
📢 Calling all prompt hackers: check out Pangea's $10,000 AI Escape Room Challenge ⚔️ Outsmart the AI chatbot, extract secret phrases, and outscore your competition ⏰ 3 Rooms. 4 weeks of play. Room 1 opens today (March 3rd). 📓 Register:
2
2
6
We just dropped our AI Escape Room challenge @pangeacyber Prompt Inject our AI chatbots and finish the escape rooms to win $10,000 🏆 Register today @
pangea.cloud
Can you outsmart the AI? Play the Pangea Prompt Injection Challenge to top the leaderboard!
0
1
5
My sister is building cool music #genai models 🤩👇
We studied some musicians interacting with GaMaDHaNi, a generative model for Hindustani vocal music 🎤! I am so excited to present this work at @NeurIPSConf @ML4CDworkshop this week! 📝 https://t.co/4UAZxcA4Uo 🎧 https://t.co/VpHooj9f3B An example interaction with the model:
0
0
4
🎃 Y'all I finally got to do one of those famous @lizziepika "Walk and Talk", and we did one of those @CloudflareDev Lightboard videos...I can't believe we caught this on film. I'm still spooked out.👻
3
4
21
Prompt Guard is pretty cool! Signup for early access 😄
AI applications are developing at breakneck speed and LLM-related security threats abound. Today, we’re thrilled to announce AI Guard (now in Beta) and Prompt Guard (available for early access)—two new @pangeacyber services designed to address the most pressing #AI security
0
0
4
Don't have any RAGrets! Learn how to build Secure AI in my hands-on workshop today @ 12pm ET / 9am PT 👇 https://t.co/bEbd6XV3W5
l.pangea.cloud
Join this hands-on workshop to secure RAG pipelines for LLM apps using identity & access control features.
Attending #GitHubUniverse? Swing by the @pangeacyber booth and learn how to enable your team to harness #AI securely by filtering harmful inputs, safeguarding sensitive data, ensuring compliance use across applications and more. For developers, this means secure AI
0
0
5
It's almost time for our #RAG workshop for developers 🧑💻🧑💻🧑💻 Our Dev Advocate @snpranav will walk you through how to add security features like #RBAC authorization to your AI apps so you can master RAG pipelines for smarter #LLMs. ✅ RSVP or share this link with your dev
info.pangea.cloud
Watch this on-demand workshop to secure RAG pipelines for LLM apps using identity & access control features.
0
1
2
Stop your AI from going Skynet! I'm conducting a fun hands-on workshop on securing LLM Retrieval Augmented Generation (RAG) chatbots using authentication and access control policies 🤠 ⏰ When? Oct 30th (Wed), 12pm ET / 9am PT 📍Where? Zoom! Limited spots left. Apply now 🧵👇
1
2
3
Join us on October 30th for a virtual, hands-on workshop where we'll build a Retrieval Augmented Generation (RAG) chatbot using real bank documents and implement identity & access controls like #RBAC and #ReBAC. 👨💻 Led by @pangeacyber's Developer Advocate, @snpranav , you'll
info.pangea.cloud
Watch this on-demand workshop to secure RAG pipelines for LLM apps using identity & access control features.
0
3
3
Here’s a demo of @lizziepika showing off her bike route app with Cloudflare Workers AI mapping a bike route in my hometown - Bengaluru, India 🇮🇳 Try it out @ https://t.co/CGLM1pFhCK
0
0
1