@sarahwordsIrish artist 🍀Saying something in as little words as possible. Studying Blockchain.

I don’t ask for much 🙏🏻🍀😂

@eduardmsmri create to make you feel something again → <https://thehiddeni.substack.com> 🌹

The strongest form of strength I've found is often the quietestIt rarely shows up in loud victories or polished storiesIt lives under the rubble of fear and doubt. It hums when I have nothing left to prove, but still choose to move forward anywayWe have to become aware of it, to hear it. And when we do, we need to trust itBecause it’s us, coming back to ourselves🌹

@selene

Hey! it's been some time i've been active, yet @kayakiko and me have been working behind the stages on Chronically Cubed! It has been long in the works, and we are so excited to share a glimpse of it with you!If you like raw, chaotic convos, you are at the right place.We are releasing the first EP soon, stay tuned 🤍

@yeastDesign by Play for an Internet that is not for us.

Since we are getting closer to the Lens Hackathon I wanted to share a few thoughts what I would love to see:_First a disclaimer I have been working with Lens and Bonsai in the past. So take that into consideration.
_
I call this what I think Lens needs. Lens is not a feed but can be. Lens is not just another chain but can be. Lens is at all but also isnt.What I think makes Lens unique is that it offers a set of incredibly powerful primitives (accounts, graphs, storage, payment rails) out of the gate.This matters for the simple reason is that if you build an app that has any social features you first need to build this entire stack before you can focus on the user experience. With lens this should be easier. So my first wish is focus on the user.From the two years of Lens we have seen a lot really cool approaches that focused on dashboards etc. But i feel we still lack more and especially different front end experiences. @bonsai has been playing around with creating entire new media formats. With their sdk you could just forget about the borrowing twitter clones and could just make a feed of media that evolves in front of the users with their interactions. Social wins if we empower creators to do new things. Think Snapchat with Stories, Tiktok with Duets, what are unique new ways we consume and create media you could build. Please dont buile just another Slack (Farcaster) …I have no data to back this up but Farcaster feels very San Francisco. There are so much more opportunities to win locally first. Why not onboard your part of the world, or your community first. Facebook started with College. What are the communities you are part of that could use a bespoke experience. I often feel if you want to be global you often end up just average. I also believe there is another option outside of the feed at all. Yes we often think about Lens as the experience we know today. Which is mainly through Orb or Hey. But what would a dex be that is built around social? What new ways for social lending could be possible? What new information or prediction markets can we create and make it more social? What are apps that take the primitives of lens and think about finance in new ways?Overall though I think there is a challenge for us as a community too to think about how we stay interoperable or composable. Farcaster has mini app and lens thought in the past about that too. Content on your feed coule be a mini app itself? What happens if we embrace AI not just as shitposters but as curators? There is a ton to do but I hope we create first and foremost more products that anyone can use. Yes a reputation protocol is cool and incredibly useful, etc but we need a new generation of user and they come in if they have fun. And fun comes with better, more interessting, new types of content and media.

@ngmislHi ✨

# Fortifying AI: Introducing Vibecondom for Safer LLM InteractionsLarge Language Models (LLMs) are revolutionizing how we interact with technology, but their increasing sophistication brings unique security challenges. Malicious actors are constantly finding new ways to exploit these systems, primarily through techniques like prompt injection – crafting inputs to bypass safety controls – and the use of hidden characters to obfuscate harmful commands or disrupt text processing. Ensuring the safety and integrity of LLM applications is paramount.The Hidden Dangers in TextPrompt injection allows attackers to manipulate LLM outputs, potentially leading to data leaks, generation of inappropriate content, or unauthorized actions. Similarly, invisible characters (like zero-width spaces or bidirectional text overrides) can be embedded within seemingly innocuous text. These hidden elements can bypass simple security filters, disguise malicious instructions, or interfere with how the LLM interprets the input, leading to unpredictable or harmful behavior.Vibecondom: A New Shield for LLM SecurityTo combat these emerging threats, a new open-source tool called Vibecondom has been developed. Written in Go, Vibecondom acts as a specialized security scanner designed specifically for the text content fed into LLMs. It serves as a critical defensive layer for AI developers, security researchers, and content moderation teams aiming to protect their systems.Core CapabilitiesVibecondom focuses on identifying subtle but dangerous patterns within text data:- Detecting Deception: It actively scans for known techniques used in prompt injection attacks and identifies various types of hidden or control characters that could signal malicious intent.
- Unmasking Obfuscation: The tool can flag potentially obfuscated content, such as Base64 encoded strings or text mixing different character scripts, which might be used to hide payloads.
- Flexible Integration: Vibecondom is designed for versatility, capable of analyzing text files stored locally or scanning content directly from remote Git repositories.
- Actionable Insights: When potential threats are detected, the tool provides clear alerts, helping teams pinpoint and investigate suspicious inputs before they compromise the LLM.Enhancing Trust in AITools like Vibecondom represent an essential step forward in securing the LLM ecosystem. By proactively identifying and flagging potentially harmful inputs, developers can build more robust defenses, fostering greater trust and reliability in AI applications.As an open-source project (MIT License), Vibecondom invites collaboration and contribution from the security community. Anyone interested in bolstering their LLM security posture is encouraged to explore the Vibecondom project on GitHub to learn more.GitHub: https://github.com/ngmisl/vibe-condom

@0xzeldaShitposter | Reply guy since birth

The new Lens apps are making me even more bullish! It's a great time to be here!

@0xjavisoftware developer, ai engineer, looking for a team to join

🔥 update on https://LCTIPS.xyz"top tip tabs"thanks to @donosonaumczuk 's suggestion, i added tabs so now you see the top tippers and also the top ppl you tipped to!it's also easier to navigate and see other account's tips:i think it's an excellent way to discover new accounts by seeing the acts of love from the ppl you love toohope you like it!!