Submissions from marble.onl

		AI doesn't replace white collar work (marble.onl)
		67 points by amarble 38 days ago \| past \| 104 comments
		I paid $170 and all I got was this demo (marble.onl)
		3 points by amarble 64 days ago \| past \| 1 comment
		I paid $170 and all I got was this stupid demo (marble.onl)
		1 point by amarble 65 days ago \| past
		Task-free intelligence testing of LLMs (marble.onl)
		69 points by amarble 3 months ago \| past \| 22 comments
		Task-free intelligence testing of LLMs (marble.onl)
		1 point by amarble 3 months ago \| past
		Intelligence is not just about task completion (marble.onl)
		1 point by amarble 3 months ago \| past
		Intelligence is not just about task completion (marble.onl)
		3 points by amarble 3 months ago \| past
		Eminembench (marble.onl)
		1 point by amarble 6 months ago \| past
		Managing LLM application performance through code standards (marble.onl)
		2 points by amarble on April 2, 2025 \| past
		Catching Claude Cheating (marble.onl)
		1 point by amarble on March 25, 2025 \| past
		Catching Claude Cheating (marble.onl)
		1 point by amarble on March 23, 2025 \| past \| 1 comment
		Scanning AI application code for vulnerabilities and performance issues (marble.onl)
		3 points by amarble on March 20, 2025 \| past
		Scanning AI application code for vulnerabilities and performance issues (marble.onl)
		2 points by amarble on March 17, 2025 \| past
		Evals are not all you need (marble.onl)
		58 points by amarble on March 3, 2025 \| past \| 12 comments
		An AI Cyber Incident in Plain Sight (marble.onl)
		2 points by amarble on Nov 24, 2024 \| past
		AI Cybersecurity Lessons from GenAI (marble.onl)
		1 point by amarble on June 22, 2024 \| past
		You won't train a better Gen AI model from your desk (marble.onl)
		2 points by andy99 on April 25, 2024 \| past
		You won't train a better Gen AI model from your desk (marble.onl)
		1 point by andy99 on April 14, 2024 \| past
		Making the data you need is a differentiator in Gen AI (marble.onl)
		6 points by andy99 on April 13, 2024 \| past
		Hyperbole in LLM Testing (marble.onl)
		1 point by andy99 on April 12, 2024 \| past
		Hyperbole in LLM Testing (marble.onl)
		2 points by andy99 on April 8, 2024 \| past
		Data bias is giving way to training bias (marble.onl)
		1 point by andy99 on Feb 27, 2024 \| past
		Supervised language model training vs. prompt engineering (marble.onl)
		1 point by andy99 on Jan 28, 2024 \| past
		Accountable language models are stored labeling effort. Prompting no substitute (marble.onl)
		1 point by andy99 on Jan 26, 2024 \| past
		AI Trends for 2024 (marble.onl)
		1 point by andy99 on Jan 1, 2024 \| past
		AI Trends for 2024 (marble.onl)
		1 point by andy99 on Dec 30, 2023 \| past
		Large Language Model Inference in Fortran (marble.onl)
		1 point by andy99 on Dec 28, 2023 \| past
		Large Language Model Inference in Fortran (marble.onl)
		2 points by andy99 on Dec 27, 2023 \| past
		Private indemnification of AI models against copyright violation (marble.onl)
		1 point by andy99 on Nov 29, 2023 \| past
		Private indemnification of AI models is a symptom of government inaction (marble.onl)
		1 point by andy99 on Oct 16, 2023 \| past
		More

HN For You