Submissions from dbreunig.com

		Enterprise Agents Have a Reliability Problem (dbreunig.com)
		2 points by dbreunig 6 days ago \| past \| discuss
		Don't Fight the Weights: Learn to Spot Contexts That Go Against Training (dbreunig.com)
		3 points by dbreunig 31 days ago \| past
		Kimi K2 RL'ed Qualitative Data to Write Better (dbreunig.com)
		4 points by nekofneko 47 days ago \| past \| 1 comment
		Glimpses of the Future: Speed and Swarms (dbreunig.com)
		3 points by vinhnx 53 days ago \| past
		Let the Model Write the Prompt (dbreunig.com)
		2 points by gglanzani 69 days ago \| past
		About That MIT Report: Enterprise AI Looks Bleak, but Employee AI Looks Bright (dbreunig.com)
		3 points by dbreunig 89 days ago \| past
		AI Companies School Like Fish to the New Use Case (dbreunig.com)
		3 points by dbreunig 3 months ago \| past
		Are Chatbots Incompatible with Advertising? (dbreunig.com)
		3 points by dbreunig 3 months ago \| past
		How to Fix Your Context (dbreunig.com)
		1 point by kiyanwang 3 months ago \| past
		How to Fix Your Context (dbreunig.com)
		93 points by itzlambda 3 months ago \| past \| 26 comments
		The AI Job Title Decoder Ring (dbreunig.com)
		91 points by dbreunig 3 months ago \| past \| 71 comments
		How will product management keep up with AI-accelerated coding? (dbreunig.com)
		3 points by dbreunig 4 months ago \| past
		GPT-OSS 20B delivers GPT-4.1 scores at 5x the speed (dbreunig.com)
		2 points by dbreunig 4 months ago \| past
		FLUX.1-Krea and the Rise of Opinionated Models (dbreunig.com)
		88 points by dbreunig 4 months ago \| past \| 34 comments
		Does the Bitter Lesson Have Limits? (dbreunig.com)
		180 points by dbreunig 4 months ago \| past \| 86 comments
		Moonshot Used RL for Qualitative Tasks to Write Better (dbreunig.com)
		2 points by dbreunig 4 months ago \| past
		Kimi 2 Became One of the Best Tool-Using Models (dbreunig.com)
		2 points by dbreunig 4 months ago \| past
		Rewriting Training Data Improved Kimi 2's Performance (dbreunig.com)
		1 point by dbreunig 4 months ago \| past
		Delegation is the AI Metric that Matters (dbreunig.com)
		2 points by lisensolikum 5 months ago \| past
		Task Delegation by Experts Is the AI Metric That Matters (dbreunig.com)
		4 points by dbreunig 5 months ago \| past \| 1 comment
		Context Fail (dbreunig.com)
		1 point by rafaepta 5 months ago \| past
		Cat Facts Cause Context Confusion (dbreunig.com)
		2 points by ingve 5 months ago \| past \| 1 comment
		How to Fix Your Context (dbreunig.com)
		1 point by kaycebasques 5 months ago \| past
		How Long Contexts Fail (dbreunig.com)
		2 points by kaycebasques 5 months ago \| past
		How Long Contexts Fail (dbreunig.com)
		10 points by ulrischa 5 months ago \| past \| 5 comments
		How Long Contexts Fail (dbreunig.com)
		1 point by bittermandel 5 months ago \| past
		Techniques for avoiding common long context fails (dbreunig.com)
		2 points by dbreunig 5 months ago \| past
		The Ways Long Contexts Fail (dbreunig.com)
		2 points by dbreunig 5 months ago \| past
		An Agentic Case Study: The Messy Work of Building a Gemini Agent to Play Pokémon (dbreunig.com)
		3 points by dbreunig 5 months ago \| past
		The drawbridges come up: the dream of a interconnected context ecosystem is over (dbreunig.com)
		111 points by dbreunig 5 months ago \| past \| 83 comments
		More