Submissions from dbreunig.com

		The AI Job Title Decoder Ring (dbreunig.com)
		59 points by dbreunig 10 hours ago \| past \| 55 comments
		How Will Product Management Keep Up with AI-Accelerated Coding? (dbreunig.com)
		3 points by dbreunig 10 days ago \| past \| discuss
		GPT-OSS 20B delivers GPT-4.1 scores at 5x the speed (dbreunig.com)
		2 points by dbreunig 15 days ago \| past
		FLUX.1-Krea and the Rise of Opinionated Models (dbreunig.com)
		88 points by dbreunig 17 days ago \| past \| 34 comments
		Does the Bitter Lesson Have Limits? (dbreunig.com)
		180 points by dbreunig 20 days ago \| past \| 86 comments
		Moonshot Used RL for Qualitative Tasks to Write Better (dbreunig.com)
		2 points by dbreunig 21 days ago \| past
		Kimi 2 Became One of the Best Tool-Using Models (dbreunig.com)
		2 points by dbreunig 22 days ago \| past
		Rewriting Training Data Improved Kimi 2's Performance (dbreunig.com)
		1 point by dbreunig 24 days ago \| past
		Delegation is the AI Metric that Matters (dbreunig.com)
		2 points by lisensolikum 37 days ago \| past
		Task Delegation by Experts Is the AI Metric That Matters (dbreunig.com)
		4 points by dbreunig 38 days ago \| past \| 1 comment
		Context Fail (dbreunig.com)
		1 point by rafaepta 44 days ago \| past
		Cat Facts Cause Context Confusion (dbreunig.com)
		2 points by ingve 47 days ago \| past \| 1 comment
		How to Fix Your Context (dbreunig.com)
		1 point by kaycebasques 51 days ago \| past
		How Long Contexts Fail (dbreunig.com)
		2 points by kaycebasques 51 days ago \| past
		How Long Contexts Fail (dbreunig.com)
		10 points by ulrischa 52 days ago \| past \| 5 comments
		How Long Contexts Fail (dbreunig.com)
		1 point by bittermandel 52 days ago \| past
		Techniques for avoiding common long context fails (dbreunig.com)
		2 points by dbreunig 56 days ago \| past
		The Ways Long Contexts Fail (dbreunig.com)
		2 points by dbreunig 59 days ago \| past
		An Agentic Case Study: The Messy Work of Building a Gemini Agent to Play Pokémon (dbreunig.com)
		3 points by dbreunig 65 days ago \| past
		The drawbridges come up: the dream of a interconnected context ecosystem is over (dbreunig.com)
		111 points by dbreunig 66 days ago \| past \| 83 comments
		Let the Model Write the Prompt: Using DSPy to Decouple Your Task from the LLM (dbreunig.com)
		4 points by dbreunig 67 days ago \| past
		Using 'Slop Forensics' to Determine Model Ancestry (dbreunig.com)
		2 points by iamflimflam1 76 days ago \| past
		Using 'Slop Forensics' to Determine Model Ancestry (dbreunig.com)
		4 points by pabs3 78 days ago \| past
		Comparing Claude System Prompts Reveal Anthropic's Priorities (dbreunig.com)
		135 points by dbreunig 78 days ago \| past \| 64 comments
		Using 'Slop Forensics' to Determine Model Lineage (dbreunig.com)
		3 points by dbreunig 83 days ago \| past
		Chatbots Trigger Guardrails Differently Based on Your Age, Gender, and Fandom (dbreunig.com)
		1 point by dbreunig 3 months ago \| past \| 1 comment
		Claude's System Prompt: Chatbots Are More Than Just Models (dbreunig.com)
		1 point by gdudeman 3 months ago \| past
		Claude's System Prompt: Chatbots Are More Than Just Models (dbreunig.com)
		2 points by misonic 3 months ago \| past
		Breaking Down Claude's 26k+ Token System Prompt (dbreunig.com)
		9 points by dbreunig 3 months ago \| past
		DuckDB is probably the most important geospatial software of the last decade (dbreunig.com)
		491 points by dbreunig 3 months ago \| past \| 165 comments
		More