dbreunig

Posts

• Techniques for avoiding common long context fails
  by dbreunigon 6/26/25, 10:17 PMwith 0 comments
• The Ways Long Contexts Fail
  by dbreunigon 6/23/25, 1:26 PMwith 0 comments
• An Agentic Case Study: The Messy Work of Building a Gemini Agent to Play Pokémon
  by dbreunigon 6/17/25, 8:04 PMwith 0 comments
• The drawbridges come up: the dream of a interconnected context ecosystem is over
  by dbreunigon 6/17/25, 12:13 AMwith 83 comments
• Let the Model Write the Prompt: Using DSPy to Decouple Your Task from the LLM
  by dbreunigon 6/15/25, 7:37 PMwith 0 comments
• Comparing Claude System Prompts Reveal Anthropic's Priorities
  by dbreunigon 6/4/25, 9:38 PMwith 64 comments
• Using 'Slop Forensics' to Determine Model Lineage
  by dbreunigon 5/30/25, 5:18 PMwith 0 comments
• Chatbots Trigger Guardrails Differently Based on Your Age, Gender, and Fandom
  by dbreunigon 5/21/25, 8:16 PMwith 1 comments
• Breaking Down Claude's 26k+ Token System Prompt
  by dbreunigon 5/8/25, 10:17 PMwith 0 comments
• DuckDB is probably the most important geospatial software of the last decade
  by dbreunigon 5/3/25, 7:30 PMwith 165 comments
• Explaining Reasoning Models: How they work, how they're built, & why they matter
  by dbreunigon 4/18/25, 8:17 PMwith 0 comments
• AI-Powered Apps Are Changing the Dynamic Between Domain Experts and Developers
  by dbreunigon 4/10/25, 2:20 PMwith 0 comments
• AI Chatbots Are Like Observational Comics
  by dbreunigon 4/8/25, 9:07 PMwith 0 comments
• ChatGPT fixes your DALL-E prompt if it's bad, but lets it be if it's good
  by dbreunigon 3/17/25, 3:57 AMwith 0 comments
• Controlling FFmpeg with natural language from the command line
  by dbreunigon 2/24/25, 8:26 PMwith 0 comments
• A 16TB Mirror of Data.gov on Source.Coop
  by dbreunigon 2/7/25, 4:29 PMwith 18 comments
• A Gentle Guide to Running a Local LLM, for Complete Beginners
  by dbreunigon 2/6/25, 6:49 PMwith 0 comments
• DeepSeek Is a Rorschach Test Revealing Each's AI Hopes and Fears
  by dbreunigon 1/31/25, 6:47 PMwith 0 comments
• The Rise of the Term "Authentic Data" Illustrates AI Anxiety
  by dbreunigon 1/23/25, 12:02 AMwith 1 comments
• Your Eval Is More Important Than the Model: Building an Example Eval
  by dbreunigon 1/9/25, 6:56 PMwith 0 comments
• The "Cyren" Song: Meta's AI profiles, Character.ai, and other fake humans
  by dbreunigon 1/3/25, 4:07 PMwith 0 comments
• A Primer on Synthetic Data: How It's Helping and Shaping LLMs
  by dbreunigon 12/19/24, 10:27 PMwith 0 comments
• DSPy Does the Prompting for You
  by dbreunigon 12/12/24, 11:20 PMwith 0 comments
• LLMs Hit the Wall: History Reveals How We Went Fast and Why We'll Go Slow
  by dbreunigon 12/5/24, 10:58 PMwith 0 comments
• Detecting DuckDB Requests in Your Webapp to Route Them to Remote DBs
  by dbreunigon 12/1/24, 9:14 PMwith 0 comments
• Surging crypto prices dampened interest in AI in 2020. Will they do it again?
  by dbreunigon 11/29/24, 4:43 PMwith 0 comments
• Transitioning from the attention era to the automation era
  by dbreunigon 11/18/24, 9:27 PMwith 2 comments
• It's the UX, Not the LLM: ChatGPT and Perplexity Can Ship a UI Google Can't
  by dbreunigon 10/31/24, 8:12 PMwith 0 comments
• Generating Descriptive Weather Reports with LLMs
  by dbreunigon 10/29/24, 11:27 PMwith 0 comments