ProjectKZ
projectkz.bsky.social
ProjectKZ
@projectkz.bsky.social
Discover engaging AI, cybersecurity, and learning tools that foster innovation, exploration, and education.
Check out MalcodeEval preliminary evaluation results on cyber capability and willingness of large language models, with a pre-release of the research paper
MalcodeEval - Rankings
MalcodeEval: a streamlined evaluation methodology designed to systematically elicit and measure the malicious capability of LLM-generated code
MalcodeEval.com
May 6, 2025 at 4:59 PM
Wonder how long it will take for them to fix it... www.theregister.com/2025/01/19/o...
ChatGPT crawler flaw opens door to DDoS, prompt injection
The S in LLM stands for Security
www.theregister.com
January 19, 2025 at 10:57 PM
Looking forward to using o3 for code! o1 is already significantly better at generating complex functional code than GPT-4o. www.reuters.com/technology/a...
OpenAI finalizes 'o3 mini' reasoning AI model version, to launch it soon
ChatGPT maker OpenAI has finalized a version of its new reasoning AI model o3 mini and would be launching it in a couple of weeks, CEO Sam Altman said on Friday.
www.reuters.com
January 18, 2025 at 11:30 AM
KaZzzle Age Chart (Last 7 Days)

Jan 03 | ██████████ 23
Jan 04 | █ 21
Jan 05 | █████ 22
Jan 06 | █████ 22
Jan 07 | █ 21
Jan 08 | ██████████ 23
Jan 09 | ███████████████ 24

Streak: 13 days | Average Age: 22

Can you beat my score? Try KaZzzle now: projectkz.com/kazzzle
KaZzzle - Challenge Your Mind!
Sharpen your math skills and challenge your friends with KaZzzle. Play now and test your mental fitness!
projectkz.com
January 9, 2025 at 9:30 PM