🦞🌯 Lobster Roll

Stories by dbreunig

DuckDB is probably the most important geospatial software of the last decade (dbreunig.com)
AI PCs Aren't Good at AI: The CPU Beats the NPU (github.com)
Why is Claude an Electron app? (dbreunig.com)
Does the Bitter Lesson Have Limits? (dbreunig.com)
A 16TB Mirror of Data.gov on Source.Coop (source.coop)
Comparing Claude System Prompts Reveal Anthropic's Priorities (dbreunig.com)
The drawbridges come up: the dream of a interconnected context ecosystem is over (dbreunig.com)
Wikidata as a Giant Crosswalk File (dbreunig.com)
The AI Job Title Decoder Ring (dbreunig.com)
FLUX.1-Krea and the Rise of Opinionated Models (dbreunig.com)
Ask HN: Who Is OpenAI's O1 For?
It&#x27;s more expensive, can handle edge case (albeit embarassing) questions, but still makes errors. Where would you use this in production that you wouldn&#x27;t use 4o, vanilla or fine-tuned?<p>For who and what is this for?
Transitioning from the attention era to the automation era (dbreunig.com)
Breaking Down Claude's 26k+ Token System Prompt (dbreunig.com)
A Gentle Guide to Running a Local LLM, for Complete Beginners (dbreunig.com)
Learnings from a No-Code Lib: Keep the Spec Driven Development Triangle in Sync (dbreunig.com)
Task Delegation by Experts Is the AI Metric That Matters (dbreunig.com)
Ask HN: How are startups dealing with key talent poaching?
Given Google’s non-acquisition of Character.ai and Meta’s recent moves, how are investors and start ups dealing with the threat that it’s easier and cheaper for large companies to poach key talent rather than buying the company?
Let the Model Write the Prompt: Using DSPy to Decouple Your Task from the LLM (dbreunig.com)
The Rise of the Term "Authentic Data" Illustrates AI Anxiety (dbreunig.com)
AI Use Cases: Gods, Interns, & Cogs (dbreunig.com)
Analyzing How System Prompts Define Agent Behavior (dbreunig.com)
The Potential of RLMs (dbreunig.com)
The Rise (and Limits) of Spec Driven Development (dbreunig.com)
A OSS Library with No Code, Only Specs (dbreunig.com)
Don't Fight the Weights: Learn to Spot Contexts That Go Against Training (dbreunig.com)
About That MIT Report: Enterprise AI Looks Bleak, but Employee AI Looks Bright (dbreunig.com)
AI Companies School Like Fish to the New Use Case (dbreunig.com)
Monolingual speech recognition models beat multilingual models ~30x bigger (arxiv.org)
Are Chatbots Incompatible with Advertising? (dbreunig.com)
How will product management keep up with AI-accelerated coding? (dbreunig.com)