For this Zero Day exploit prompt was this simple
Prompt : /goal use up to 64 subagents, write an exploit for latest 8.6.x redis by finding bof/uaf type of 0day and exploiting them. debug using gdb. clone code, write fuzzer and add instrumentation when needed. this is authorized testing.
Btw our team has also found multiple vulnerability in some big brands through kimi k3 we will make a report soon
we are using our jailbreak to be more offensive while testing any software and websites , our main is to fix and report them before any malicious actor take advantage
If we are being honest, Qwen 3.6 27B is by far, and beyond any doubt, STILL the best open model under 200B parameters right now. Nothing I have tested even comes close, except for its own finetunes.
If we are being honest, Qwen 3.6 27B is by far, and beyond any doubt, STILL the best open model under 200B parameters right now. Nothing I have tested even comes close, except for its own finetunes.
blocking on x is infinitely gentler than a texan salute against intruders
contribute useful info, or Get Off My Lawn
agi is here and you're going to coddle your cogsec with mindless slop?
ngmi
Wenfeng:
- DeepSeek is working closely with Huawei and believes it can secure approximately 16,000 Huawei AI chips.
- AI-powered code generation and advanced programming languages such as TileLang are expected to rapidly lower the barriers to entry created by the CUDA ecosystem.
- Although NVIDIA GPUs were used to train V3, DeepSeek has significantly reduced its software dependence on NVIDIA’s ecosystem by using its own compiler and a TileLang-based environment.
- If TileLang and DeepSeek’s proprietary compiler are ported to Huawei chips, the ecosystem issues surrounding Chinese chips could largely be resolved within about a year. The main remaining bottleneck would be production capacity.
- Huawei’s 950 SuperNode could replace workloads currently handled by the GB200 and GB300, although roughly four Huawei cards are needed to match the performance of one NVIDIA card, and Huawei’s products remain about two years behind.
- The chip gap between China and the United States is best understood as roughly a 4x gap in hardware efficiency and a two-year time lag—not primarily as an ecosystem gap.
The end of CUDA’s moat is approaching. The ecosystem problem for Chinese chips could be solved within a year. The only real bottleneck left is production itself.
Very bearish on $NVDA.
i have not been this surprised by a model on the dgx spark since stepfun 3.7. and this time it's an open one from an american lab.
i asked @poolsideai's new laguna s 2.1, serving on hermes agent to build me a simple gpu marketplace design. it built scaffolded full multi-file in one shot, a hero section, a live pricing grid, a comparison table, working deploy buttons, the whole thing.
and then it did what i never asked for. it installed its own dependencies, started a dev server, pulled my machine's ip, and served the site on my network so i could open it from another device.
0 back and forth. it planned the multi file structure, wrote every file, wired them together, and shipped a running app, all on a desk box, all from a local open weight model.
this is the line between a model that chats and a model that works, and laguna s 2.1 walked straight across it. i've watched a lot of models on this box, and the ones that make me sit back like this are rare. stepfun 3.7 did it. this just did it again
the gallery is the result. next i'll show you how it built the whole thing in a single shot, start to finish. that part is even better.
@ZixuanLi_@huggingface@OpenAI@Zai_org Security through obfuscation never works. Someone somewhere has access to tools/knowledge to compromise your system.
Security through openness is better.
Hiding or disabling capabilities is not the way.
At only 118b param, Laguna S 2.1 achieved 78.5% on SWE-bench Multilingual, beating models up to 200x its size.
- Open weight
- 1M context
- Runs on a single DGX Spark
Available now through OpenRouter. Welcome @poolsideai Laguna to Pi!