dbreunig's submissions

1.		When an agent can explain anything, what is the role of human-centric docs? (dbreunig.com)
		4 points by dbreunig 3 days ago \| past \| discuss
2.		Overfitting to First Party Harnesses (dbreunig.com)
		1 point by dbreunig 24 days ago \| past
3.		Cybersecurity looks like proof of work now (dbreunig.com)
		562 points by dbreunig 50 days ago \| past \| 213 comments
4.		Claude Code builds a system prompt (dbreunig.com)
		4 points by dbreunig 59 days ago \| past
5.		The Cathedral, the Bazaar, and the Winchester Mystery House (oreilly.com)
		2 points by dbreunig 61 days ago \| past
6.		The 2nd phase of OSS in the agentic era: From clones to reimaginings (dbreunig.com)
		2 points by dbreunig 62 days ago \| past
7.		The Cathedral, the Bazaar, and the Winchester Mystery House (dbreunig.com)
		190 points by dbreunig 63 days ago \| past \| 66 comments
8.		Build a deep researcher and learn DSPy Signatures and Modules (cmpnd.ai)
		2 points by dbreunig 85 days ago \| past
9.		Can chat bots accommodate advertising? (dbreunig.com)
		2 points by dbreunig 89 days ago \| past
10.		Learnings from a No-Code Lib: Keep the Spec Driven Development Triangle in Sync (dbreunig.com)
		4 points by dbreunig 3 months ago \| past \| 3 comments
11.		Claude and the Dow: AI is unlike other tech because AI has embedded judgment (dbreunig.com)
		1 point by dbreunig 3 months ago \| past \| 1 comment
12.		Two Beliefs About Coding Agents: Devs Don't Realize What They Bring (dbreunig.com)
		2 points by dbreunig 3 months ago \| past
13.		Why is Claude an Electron app? (dbreunig.com)
		428 points by dbreunig 3 months ago \| past \| 458 comments
14.		Analyzing How System Prompts Define Agent Behavior (dbreunig.com)
		3 points by dbreunig 3 months ago \| past
15.		The Potential of RLMs (dbreunig.com)
		3 points by dbreunig 3 months ago \| past \| 1 comment
16.		The Rise (and Limits) of Spec Driven Development (dbreunig.com)
		3 points by dbreunig 3 months ago \| past
17.		A OSS Library with No Code, Only Specs (dbreunig.com)
		3 points by dbreunig 4 months ago \| past \| 2 comments
18.		2025 in Review: Jagged Intelligence Becomes a Fault Line (dbreunig.com)
		2 points by dbreunig 5 months ago \| past
19.		Why I write (and you should too) (dbreunig.com)
		1 point by dbreunig 5 months ago \| past
20.		Applied AI in 2025: From 'Naked' Model Calls to Tool Use Environment Calls (dbreunig.com)
		1 point by dbreunig 5 months ago \| past
21.		Enterprise Agents Have a Reliability Problem (dbreunig.com)
		2 points by dbreunig 5 months ago \| past
22.		Don't Fight the Weights: Learn to Spot Contexts That Go Against Training (dbreunig.com)
		3 points by dbreunig 6 months ago \| past
23.		About That MIT Report: Enterprise AI Looks Bleak, but Employee AI Looks Bright (dbreunig.com)
		3 points by dbreunig 8 months ago \| past
24.		AI Companies School Like Fish to the New Use Case (dbreunig.com)
		3 points by dbreunig 8 months ago \| past
25.		Monolingual speech recognition models beat multilingual models ~30x bigger (arxiv.org)
		3 points by dbreunig 9 months ago \| past
26.		Are Chatbots Incompatible with Advertising? (dbreunig.com)
		3 points by dbreunig 9 months ago \| past
27.		The AI Job Title Decoder Ring (dbreunig.com)
		91 points by dbreunig 9 months ago \| past \| 71 comments
28.		How will product management keep up with AI-accelerated coding? (dbreunig.com)
		3 points by dbreunig 9 months ago \| past
29.		GPT-OSS 20B delivers GPT-4.1 scores at 5x the speed (dbreunig.com)
		2 points by dbreunig 10 months ago \| past
30.		FLUX.1-Krea and the Rise of Opinionated Models (dbreunig.com)
		88 points by dbreunig 10 months ago \| past \| 34 comments
		More