dbreunig's submissions

1.		Analyzing How System Prompts Define Agent Behavior (dbreunig.com)
		3 points by dbreunig 1 day ago \| past \| discuss
2.		The Potential of RLMs (dbreunig.com)
		3 points by dbreunig 5 days ago \| past \| 1 comment
3.		The Rise (and Limits) of Spec Driven Development (dbreunig.com)
		3 points by dbreunig 8 days ago \| past \| discuss
4.		A OSS Library with No Code, Only Specs (dbreunig.com)
		3 points by dbreunig 36 days ago \| past \| 2 comments
5.		2025 in Review: Jagged Intelligence Becomes a Fault Line (dbreunig.com)
		2 points by dbreunig 47 days ago \| past
6.		Why I write (and you should too) (dbreunig.com)
		1 point by dbreunig 49 days ago \| past
7.		Applied AI in 2025: From 'Naked' Model Calls to Tool Use Environment Calls (dbreunig.com)
		1 point by dbreunig 57 days ago \| past
8.		Enterprise Agents Have a Reliability Problem (dbreunig.com)
		2 points by dbreunig 70 days ago \| past
9.		Don't Fight the Weights: Learn to Spot Contexts That Go Against Training (dbreunig.com)
		3 points by dbreunig 3 months ago \| past
10.		About That MIT Report: Enterprise AI Looks Bleak, but Employee AI Looks Bright (dbreunig.com)
		3 points by dbreunig 5 months ago \| past
11.		AI Companies School Like Fish to the New Use Case (dbreunig.com)
		3 points by dbreunig 5 months ago \| past
12.		Monolingual speech recognition models beat multilingual models ~30x bigger (arxiv.org)
		3 points by dbreunig 5 months ago \| past
13.		Are Chatbots Incompatible with Advertising? (dbreunig.com)
		3 points by dbreunig 5 months ago \| past
14.		The AI Job Title Decoder Ring (dbreunig.com)
		91 points by dbreunig 5 months ago \| past \| 71 comments
15.		How will product management keep up with AI-accelerated coding? (dbreunig.com)
		3 points by dbreunig 6 months ago \| past
16.		GPT-OSS 20B delivers GPT-4.1 scores at 5x the speed (dbreunig.com)
		2 points by dbreunig 6 months ago \| past
17.		FLUX.1-Krea and the Rise of Opinionated Models (dbreunig.com)
		88 points by dbreunig 6 months ago \| past \| 34 comments
18.		Does the Bitter Lesson Have Limits? (dbreunig.com)
		180 points by dbreunig 6 months ago \| past \| 86 comments
19.		Moonshot Used RL for Qualitative Tasks to Write Better (dbreunig.com)
		2 points by dbreunig 6 months ago \| past
20.		Kimi 2 Became One of the Best Tool-Using Models (dbreunig.com)
		2 points by dbreunig 6 months ago \| past
21.		Rewriting Training Data Improved Kimi 2's Performance (dbreunig.com)
		1 point by dbreunig 6 months ago \| past
22.		Task Delegation by Experts Is the AI Metric That Matters (dbreunig.com)
		4 points by dbreunig 7 months ago \| past \| 1 comment
23.		Ask HN: How are startups dealing with key talent poaching?
		4 points by dbreunig 7 months ago \| past \| 2 comments
24.		Techniques for avoiding common long context fails (dbreunig.com)
		2 points by dbreunig 7 months ago \| past
25.		The Ways Long Contexts Fail (dbreunig.com)
		2 points by dbreunig 7 months ago \| past
26.		An Agentic Case Study: The Messy Work of Building a Gemini Agent to Play Pokémon (dbreunig.com)
		3 points by dbreunig 8 months ago \| past
27.		The drawbridges come up: the dream of a interconnected context ecosystem is over (dbreunig.com)
		111 points by dbreunig 8 months ago \| past \| 83 comments
28.		Let the Model Write the Prompt: Using DSPy to Decouple Your Task from the LLM (dbreunig.com)
		4 points by dbreunig 8 months ago \| past
29.		Comparing Claude System Prompts Reveal Anthropic's Priorities (dbreunig.com)
		135 points by dbreunig 8 months ago \| past \| 64 comments
30.		Using 'Slop Forensics' to Determine Model Lineage (dbreunig.com)
		3 points by dbreunig 8 months ago \| past
		More