HACKERSCHOICE

thanks for the answers. it's mostly what i suspected. besides the usual suspects i guess finding vulnerabilities needs some degree of creativity that llms can't deliver.

damn, i get ptsd symptoms everytime i see the word captcha. this nearly endless loop of buses, hydrants and motorcycles...

it really depends on your goals, but web red teaming works perfectly fine and i think defense will lose after 2 years of productive so called "prompt engineering". its a question of your personal time, if you have the time to always compare the (almost daily released) different models. but you dont have to spend a single cent to use ai that is, at least, capable of doing stuff what the pr shit companys like asstrophic and closedai are telling us theyre working on. basically its a game of catching the most free tokens from either openrouter (https://openrouter.ai/models?max_price=0&q=free&order=newest), kilocode (https://kilo.ai/docs/gateway) and opencode (https://opencode.ai/docs/zen/). you can let bots create api keys and accounts for these gateways. with an nvidia card, you could use cuda, ollama and host uncensored, for example gemma 4 heretic/uncensored, on your local machine. or on a mash of victim mashinces if you use them as ollama nodes and split the load the dirtiest way is to use context7 mcp (https://context7.com/), which is huge collection of github repos and docs use qdrant with a 2048 vect0r size with this model https://openrouter.ai/nvidia/llama-nemotron-embed-vl-1b-v2:free and set up a vscode instance with kilo code extention for full fire capacaties you dont have to use agents, its bullshit. give your llm (less guardrails with chinese models like tencent, xiaomi, z-ai and deepseek and stuff) a well written prompt, point to online sources, give it context and a well structured folder and .md file base. you can get aditional mcp servers like https://github.com/CommonHuman-Lab/nyxstrike, https://github.com/SHAdd0WTAka/Zen-Ai-Pentest, or https://github.com/vxcontrol/pentagi. mcp servers are something like addons for llm but also bring skills an llm normally wouldnt have, like python scripts that do api stuff i think it gives you a bright variety of things and stuff you can do with it, which isnt linked to classical hacking. im not into instagram re

thanks for the extensive answer. i really appreciate it.

there is cool article for a vulnerability research using AI agents https://devansh.bearblog.dev/needle-in-the-haystack/

looks interesting. i will need some time to really read through this.

anybody got experience with ssh in a-shell app on ios? after copying the secret into config, i can connect to my segfault host, but i always have to type the root pw. it claims the private key file is not there, although i copied it also to .ssh and made sure it has 600 permissions 🤔

New Website for AI bots: https://www.vincentschmalbach.com/time-serves-ai-bots-a-different-website/

but thanks for the link! so i guess the time has come when humans have to start disguising as ai/robots to fly under the radar 🤦

Home path changes every time the app or phone is launched solve that problem save in ~/.ssh/config

ofc i need to save in .ssh/config, but THAT itself is in ~/Documents/ and not ~/ as on every sane system 😁

sure. the ~ i already knew as everywhere 😆 but the issue was/is that apparently $HOME != ~ in contrast to every other system i know 😏

That's why I hate iOS.💔