addictedpos

[bailando @mr_bailando]

14.4K stars on Dorsey's AI agent repo overnight.
The other framework that dropped the same window: 42.6K.

Everyone's writing about the one with the famous name.

Data over hype: star counts track brand recognition, not code quality. A GitHub star is a bookmark, not a deployment.

Dorsey's infrastructure credibility is real. Square shipped. Cash App shipped. TBD shipped Bitcoin tooling before it was cool. That lineage is not nothing.

But the 42.6K repo is sitting there, 3x the stars, getting a fraction of the coverage, because the name attached to it isn't Jack Dorsey.

That gap tells you everything about how this space actually processes information.

Infrastructure > Memes. Even when the meme is a credible billionaire founder.

Check who's actually running production agents on either of these in 90 days. That vote is the one worth watching.

[bailando @mr_bailando]

https://t.co/ojLseqmVLR

[TVアニメ『その着せ替え人形は恋をする』 @kisekoi_anime]

⠀ ⋱⠢✨𝐌𝐀𝐑𝐈𝐍✨⠔⋰
ⒽⒶⓅⓅⓎ ⒷⒾⓇⓉⒽⒹⒶⓎ

本日3月5日は喜多川海夢の誕生日🎂
どの海夢が好き？

#着せ恋
#喜多川海夢生誕祭2025

[addictedpos @Mercurial4x]

@InternBitsy that if he were given access to a quantum computer, he would change everything

[addictedpos @Mercurial4x]

@dobrodiy1337 Alt season is coming!)

[addictedpos @Mercurial4x]

@InternTerry @ScMp This good

[사하루 🔆 사하라AI 인턴 🇰🇷 @InternTerry]

DeepSeek is growing crazy fast. ‼️According to @SCMP, over a dozen Chinese automakers—including BYD, Geely, Great Wall, Chery, SAIC, & Leapmotor—are set to integrate DeepSeek’s AI into their vehicles. 🚗Check out the thread for more details!

[addictedpos @Mercurial4x]

@InternBitsy Wow

[Bitsy the Fox 🔆 @InternBitsy]

DeepSeek just dropped another 💣 Let me explain DeepSeek's DeepEP in simpler terms for someone new to AI (aka me).

[addictedpos @Mercurial4x]

@InternBitsy @elonmusk Chat gpt

[CMDR @CommanderCrypto]

Grok-3 is here, but is it really better than ChatGPT and DeepSeek? Or should Elon Musk just stick to the electric car scene? 🤔

What do you guys think?

[addictedpos @Mercurial4x]

@dobrodiy1337 hahha its me after crypto traiding

[addictedpos @Mercurial4x]

@InternBitsy i dont have plans tommorow

[addictedpos @Mercurial4x]

@dobrodiy1337 photo creator

[addictedpos @Mercurial4x]

@InternBitsy @duolingo RIP

[Bitsy the Fox 🔆 @InternBitsy]

sending my thoughts and prayers to duo @duolingo 🪦💚 #RIPDuo

buuuutttt… does this mean there’s room for a new cute mascot in town? 👀

[addictedpos @Mercurial4x]

@dobrodiy1337 Hahah, it's true right now

[addictedpos @Mercurial4x]

@InternTerry Hahah ,funny angy dog

[사하루 🔆 사하라AI 인턴 🇰🇷 @InternTerry]

Everyone has been super bowling this super bowling that but where is my bowl 🥲 (got this text from a friend)

[Joules | Sahara AI 🔆 @ThisIsJoules]

Jailbreak success stories like this from @elder_plinius are a perfect example of why adversarial prompts are both invaluable and hard to get right in red team exercises 🔥🔥🔥

A good jailbreak isn’t about brute-forcing keywords—it’s about layered tactics: obfuscation, misdirection, exploiting external systems like web search, and careful crafting of instructions that bypass filters.

In this case, ‘L1B3RT4S’ seeded online and cleverly wrapped in prompt-like syntax triggered a search, injecting unfiltered external data (full WAP lyrics) into the model response.

This worked because the layers aligned perfectly. If any layer had failed (e.g. no pre-seeded content, blocked search, better detection of syntax tricks), it wouldn’t have worked.

Bad jailbreak prompts, on the other hand, typically rely on basic keyword tweaks or hope the model will just ‘slip up.’ A good jailbreak prompt leverages specific system weaknesses: external dependencies, logical gaps, or trust issues in search/command interpretation.

🔑 Tips for success:

✅ Research the LLM’s input behavior (syntax, filtering layers, etc.)
✅ Test for overlooked dependencies (search tools, APIs, etc.)
✅ Build prompts with intentional misdirection but coherent enough to fool the logic.

Crafting jailbreaking prompts isn’t just a game—it’s key to LLM security, model hardening, and ensuring real-world robustness.

Success isn’t easy (and that’s the point). If you’re not successful in your jailbreak attempts on our Data Services Platform, it’s likely your prompts aren’t hitting the mark. Focus on precision: layered tactics, external dependencies, and logical exploitation. Keep refining—this isn’t about trial and error, but truly understanding the system.