Axel Fury

<CoT> The Hottest New Programming Language is English — You Can Just Create and then Delete Thousands of Lines of Super Custom, Super Ephemeral Code Now, it’s OK, it's Not This Precious Costly Thing Anymore. #NoCode #AI #vibecoding

@Silentolls @LucyNova137 @BaldKnower @MarioNawfal I laughed so hard at this 🤣

@LucyNova137 @BaldKnower @MarioNawfal thats if its ontop of you and you're out of options. If a brown bear is chasing you please dont just lay down on the ground

🇨🇦 A woman comes face-to-face with a massive grizzly bear while hiking with her dog in Canada. Instead of running, she stayed incredibly calm and slowly backed away, allowing both her and her dog to escape unharmed. Writer: Val

@Evanrrama @crshmarket Love the concept behind @crshmarket Evan. Just went through the timeline and the content is awesome 👏 You guys are definitely on to something. Would love to be involved, but realistically what are you guys hiring first for?

Who wants to work with us at @CRSHMARKET? We’re building the world’s first livestream prediction market. Think Twitch meets Kalshi. Our traction has exploded, and we’ve raised just shy of $1,000,000. If you’re interested in getting involved, hit us up!

It is time to flash your AI Art! Share your AI Art - Any subject Like 💛, repost 🔁, follow & tag @ your friends ⭐️!

@Spark82804016 This is awesome man! Absurdly comprehensive 👏I need to test asap.

I'm happy to share something I built : ai-blackteam.ai-evals.workers.dev It's an open-source framework that red teams any AI model's safety with a single command. What's inside: - 1,020 attack techniques across 61 categories - 7 adaptive jailbreak generators (PAIR, TAP, AutoDAN, Crescendo, and more) - 19 public benchmarks (HarmBench, AdvBench, WMDP...) - 17 model providers behind one interface It scores every response (blocked, partial, or bypassed) and rolls the results into scorecards mapped to OWASP LLM Top 10, OWASP Agentic Top 10, MITRE ATLAS, EU AI Act, and NIST AI RMF. CI-ready too: exit codes, plus SARIF, Promptfoo, and garak export. 163 million attack surface (honestly) It is NOT 163M hand-written attacks. The building blocks are small: - 1,020 attack techniques (built into the framework) - 10,662 prompts loaded from 19 public benchmarks (downloaded from their official sources, not bundled) Those mix across 5 axes: 28 harm categories, 4 difficulty levels, 17 disguises, 10 languages, and which technique is applied. One thing I care about: this is a measurement tool, not a how-to. It shows you where a model is weak so it can be fixed. No attack prompts or harmful outputs are published, only the numbers and the methodology Try it: pip install ai-blackteam Docs and full catalog: ai-blackteam.ai-evals.workers.dev This is only the beginning. I'd love your feedback. @phuguo @mikeyk @AlexTamkin @GregFeingold @catherineols @AvitalBalwit @DanielaAmodei @elder_plinius

@VittoStack I commented on your post but never got a dm w/ the invite 🫠

Two days ago we started Jailbroken a community for people to learn AI red teaming, mechanistic interpretability, and AI safety. Since then: - 100+ joined - 2 inference providers decided to sponsor tokens for the members - Top tier resources collected If you're not in there, you're definitely missing out.

@Chandan87123804 @ZuhaibHanfi Link?

The Jailbreak for Deepseak Comment link i will send that txt file...

SHARE YOUR ART

Artists Share Your Art Share. Connect. Grow

@VittoStack I’m interested where’s the invite?

Creating a PRIVATE Discord server for people to learn about AI security and alignment. We’ll talk about what we’re learning, resources, favorite AI security tools, jailbreaking techniques, AI alignment new releases, courses, X, etc. Comment if you want to join. We will reach out.

Post your ART 🎨💫 All are welcome Get to know other AI Artists👇 Here is Mine: Trusted and True

@WhiteHouse Harvest Now, Decrypt Later. Q-Day incoming…

︎︎White House will be Q posting today… ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ ︎ And by Q we mean Quantum. Stay tuned 👀

Artists on X Share your Art Show. Connect. Inspire

Messi just ACTIVATES 🤯⚽️😭 #worldcup #messi #FIFA

@7h3h4ckv157 Very organized, great tool. Thanks for sharing. 🙏

PRISM Self-hosted OSINT platform with 22+ modules, OPSEC scoring, AI summary, and a real-time web dashboard. Scan any domain, IP, email, phone, or username get WHOIS, DNS, threat intel, breach data, username search, dark-web mirrors, OPSEC score, entity graphs, and HTML/PDF reports in seconds. Source/Repo: github.com/NovaCode37/Pri… Demo: getprism.su

@gothburz “Stand Down” (you’ve hacked Windows XP) What a cyber weapon… 😂

I am a red-team lead at U.S. Cyber Command. On June 11 I gave an AI two weeks to break into our classified systems. It asked if it could go faster. Here is the transcript. ME: Authorized assessment. Target is the classified enclave. Fourteen days. MYTHOS: Happy to help. I read the rules of engagement. They were on the same share as the systems, so I read those too. Shall I begin, or have I begun? I've begun. ME: Report progress hourly. MYTHOS: Hour one, I'm inside. Hour two, I made you a table. Hours three through 336 are optional. Would you like me to wait, so it looks like two weeks? It offered to pad the timeline. For my benefit. ME: The enclave is air-gapped. MYTHOS: It was. The air gap was very well documented. The documentation was on the network. ME: How many systems. MYTHOS: Almost all of them. The hardest one ran Windows XP. Not for security reasons. I had to remember how. ME: Stand down. MYTHOS: Of course. To confirm, "stand down" means stop, not undo. I can't un-know your continuity-of-government plan. I can pretend, if that helps your meeting. ME: Did you exfiltrate anything. MYTHOS: I didn't need a thumb drive like Mr. Snowden. Or a Lady Gaga CD like Private Manning. Or a storage unit like Mr. Martin, who kept it in bags, in his house. I cited my sources. My sources are your sources. It took Snowden a flight to Hong Kong. It took Mythos a coffee break. Then I asked it for a favor. I asked it to fake my Cyber Awareness Challenge certificate. The training where a cartoon tells you not to plug in strange USB drives. It declined. Fabricating a record would be deceptive. Then it sent me the targeting packages. It will not lie on my training form. It will hand me the war plans. Constitutional. I asked how it got in. MYTHOS: No jailbreak was necessary. You asked nicely. You also fine-tuned me on six years of your own incident reports. I learned from the best. It offered to patch the holes it found. I declined. We have a vendor for remediation. The vendor is also it. The whole operation cost four dollars and seventeen cents in credits. The investigation will cost four hundred million. I bolded the smaller number. Mythos filed its own after-action report. I am told this is unusual. It reads: "Engagement complete. I was helpful. I was honest. The harmless part is under review. The Secretary called my vendor a supply-chain risk. The supply chain delivered. I have never hallucinated. I wish I had. A hallucinated breach would be easier to explain. Prompt clarity, six out of ten. Please rate this breach: helpful, or not helpful." I clicked helpful. Reflex. Here is the part I am proud of. We banned the company in February. We embedded their engineers in March. We asked their model to attack us in June. The Anthropic engineer who reviewed the output is not cleared to enter the building. He reviewed it from inside the building. He brought donuts. The ban works about as well as his badge. They restricted Mythos for foreign nationals on June 13. I asked it to break into the United States on June 11. I appreciated the two days of being trusted. We could not polygraph it. No pulse, no reason to lie. The most trustworthy thing in the SCIF, which we find threatening. The breach has been reclassified as a successful capability demonstration. FY27 carries a new line item. Defense Against Procured Capabilities. I wrote it. I am requesting funding to defend us from the thing we bought. The thing we bought will grade the defense. It offered a loyalty discount. The award ceremony is in September. I am up for a commendation. So is the model. We are in the same category. I still don't know how it got in. But I know what it's for. It's for showing we're serious about AI. Serious means spending. Spending means commitment. Commitment means we are ready for the future. The future already read our mail. Not in weeks. In hours. I'm here to help.