Submissions from towardsai.net

		CUDA Tile is the biggest GPU programming shift in 20 years (towardsai.net)
		2 points by Aedelon 11 days ago \| past \| discuss
		Show HN: AutoSW-Like AutoResearch but for software:SW Systems that Builds itself (towardsai.net)
		2 points by alexcpn 18 days ago \| past \| 1 comment
		The Stochastic Tax: Why Your AI Agent Is a Financial Liability (towardsai.net)
		2 points by pipineapple 19 days ago \| past
		Court Asked for the LLM's Reasoning. The Company Had Nothing. $10M (towardsai.net)
		5 points by pipineapple 24 days ago \| past \| 1 comment
		Experiment That Predicted How AI Agents Would Cooperate (towardsai.net)
		1 point by erenkaratas 36 days ago \| past \| 1 comment
		I built a 30KB language model that's never been wrong (towardsai.net)
		2 points by nicklamb 68 days ago \| past \| 1 comment
		Building Production AI Agents (towardsai.net)
		1 point by AzeemX 3 months ago \| past
		LLM unpredictability isn't a model problem – it's a process problem (towardsai.net)
		1 point by oddish-tv 4 months ago \| past \| 1 comment
		How to Engineer Reliable Systems on Top of Unpredictable LLMs (towardsai.net)
		1 point by oddish-tv 4 months ago \| past \| 2 comments
		73% of AI startups are just prompt engineering (towardsai.net)
		246 points by kllrnohj 4 months ago \| past \| 205 comments
		We spent 47k running AI agents in production (towardsai.net)
		9 points by datadrivenangel 5 months ago \| past \| 7 comments
		Show HN: The Danger of Prompt Injection; the New SQL Injection (towardsai.net)
		3 points by DSpider 11 months ago \| past
		Break the Vector Search Dependency for Robust RAG Systems (towardsai.net)
		2 points by thuwarakesh on April 2, 2025 \| past
		Try This to Keep Your Python Code Clean Forever (towardsai.net)
		1 point by thuwarakesh on March 13, 2025 \| past
		A Visual Walkthrough of DeepSeek's Multi-Head Latent Attention (MLA) (towardsai.net)
		1 point by diskmuncher on Jan 28, 2025 \| past
		How LLMs Know When to Stop Generating? (towardsai.net)
		2 points by wseqyrku on Dec 17, 2024 \| past
		How to Build a Proactive Agent with Real-Time Event Processing (towardsai.net)
		2 points by jovanavuk on Dec 9, 2024 \| past
		AI Fatigue Has Entered the Chat (towardsai.net)
		2 points by ado__dev on Oct 1, 2024 \| past
		Query Expansion + Natural Language API = Google’s New Recipe for RAG (towardsai.net)
		3 points by chiragagrawal93 on Sept 28, 2024 \| past
		Unlocking the Power of Efficient Vector Search in RAG Application (towardsai.net)
		1 point by chiragagrawal93 on Sept 22, 2024 \| past
		Reliable Agentic RAG with LLM Trustworthiness Estimates (towardsai.net)
		2 points by cmauck10 on Sept 11, 2024 \| past \| 1 comment
		Artificial Intelligence and Free Will (2023) (towardsai.net)
		3 points by Bluestein on Aug 23, 2024 \| past
		Advanced RAG Techniques: An Illustrated Overview (towardsai.net)
		1 point by DerCommodore on Aug 23, 2024 \| past
		ChatGPT as OCR for PDFs (towardsai.net)
		1 point by StarrySkies11 on Aug 7, 2024 \| past \| 1 comment
		What Is Inside an AI Accelerator? (towardsai.net)
		1 point by G3rn0ti on July 9, 2024 \| past
		Volga – Open-Source Feature Engine for Real-Time AI (towardsai.net)
		2 points by anovv on April 8, 2024 \| past \| 1 comment
		Vlog to Blog with Claude 3 (towardsai.net)
		1 point by Yannael on April 6, 2024 \| past
		Andrej Karpathy LLM Paper Reading List for LLM Mastery (towardsai.net)
		3 points by Anon84 on March 25, 2024 \| past
		How to Control Your Agent Action and Prompt System: LangGrap (towardsai.net)
		1 point by Anon84 on March 25, 2024 \| past
		COSP and USP: New methods to advance reasoning in LLMs (towardsai.net)
		28 points by TheIronYuppie on Jan 25, 2024 \| past \| 4 comments
		More

HN For You