Submissions from dbreunig.com

		My CCPA Dialog with OpenAI (2023) (dbreunig.com)
		1 point by dbreunig 2 days ago \| past \| discuss
		What We Can Learn from Claude's Fable 5.1 System Prompt Changes (dbreunig.com)
		4 points by dbreunig 5 days ago \| past \| discuss
		Who Taught the Models to Do That? (dbreunig.com)
		5 points by Brajeshwar 12 days ago \| past \| discuss
		Fable and the end of the free lunch (dbreunig.com)
		225 points by dbreunig 20 days ago \| past \| 263 comments
		Manage agent loadouts with drskill – "brew doctor for agents" (dbreunig.com)
		1 point by jesserobbins 25 days ago \| past \| 2 comments
		Harnesses Are "Situated Agents" (dbreunig.com)
		1 point by dbreunig 26 days ago \| past
		Manage Your Agent's Loadout with Dr Skill (dbreunig.com)
		2 points by dbreunig 47 days ago \| past
		Understanding the Dynamics of the AI Ecosystem with Pace Layers (dbreunig.com)
		1 point by gmays 67 days ago \| past
		Understanding the Dynamics of the AI Ecosystem with Pace Layers (dbreunig.com)
		3 points by dbreunig 70 days ago \| past \| 1 comment
		The Problem Is Prompt Debt (dbreunig.com)
		3 points by ljoshua 79 days ago \| past
		The Problem Is Prompt Debt (dbreunig.com)
		4 points by ingve 80 days ago \| past \| 1 comment
		The Problem is Prompt Debt: You can't be model agnostic and hand-tune prompts (dbreunig.com)
		4 points by dbreunig 81 days ago \| past
		When an agent can explain anything, what is the role of human-centric docs? (dbreunig.com)
		4 points by dbreunig 3 months ago \| past
		The Cost of Overfitting the Harness (dbreunig.com)
		1 point by gmays 4 months ago \| past \| 1 comment
		The Cost of Overfitting the Harness (dbreunig.com)
		2 points by Brajeshwar 4 months ago \| past
		Overfitting to First Party Harnesses (dbreunig.com)
		1 point by dbreunig 4 months ago \| past
		Lessons for Agentic Coding: What should we do when code is cheap? (dbreunig.com)
		270 points by ingve 4 months ago \| past \| 237 comments
		Cybersecurity Looks Like Proof of Work Now (dbreunig.com)
		5 points by brie22 5 months ago \| past
		Cybersecurity looks like proof of work now (dbreunig.com)
		562 points by dbreunig 5 months ago \| past \| 214 comments
		Claude Code builds a system prompt (dbreunig.com)
		4 points by dbreunig 5 months ago \| past
		The 2nd phase of OSS in the agentic era: From clones to reimaginings (dbreunig.com)
		2 points by dbreunig 5 months ago \| past
		The Cathedral, the Bazaar, and the Winchester Mystery House (dbreunig.com)
		190 points by dbreunig 5 months ago \| past \| 66 comments
		Can chat bots accommodate advertising? (dbreunig.com)
		2 points by dbreunig 6 months ago \| past
		Learnings from a No-Code Lib: Keep the Spec Driven Development Triangle in Sync (dbreunig.com)
		4 points by dbreunig 6 months ago \| past \| 3 comments
		Claude and the Dow: AI is unlike other tech because AI has embedded judgment (dbreunig.com)
		1 point by dbreunig 6 months ago \| past \| 1 comment
		Two Beliefs About Coding Agents: Devs Don't Realize What They Bring (dbreunig.com)
		2 points by dbreunig 6 months ago \| past
		Why is Claude an Electron app? (dbreunig.com)
		428 points by dbreunig 6 months ago \| past \| 458 comments
		System Prompts Define Agent Behavior (dbreunig.com)
		2 points by Brajeshwar 7 months ago \| past
		Analyzing How System Prompts Define Agent Behavior (dbreunig.com)
		3 points by dbreunig 7 months ago \| past
		The Potential of RLMs (dbreunig.com)
		1 point by gmays 7 months ago \| past
		More