| | Breaking Down Claude's 26k+ Token System Prompt (dbreunig.com) |
|
9 points by dbreunig 2 days ago | past | discuss
|
|
| | DuckDB is probably the most important geospatial software of the last decade (dbreunig.com) |
|
491 points by dbreunig 7 days ago | past | 165 comments
|
|
| | Explaining Reasoning Models: How they work, how they're built, & why they matter (dbreunig.com) |
|
2 points by dbreunig 22 days ago | past
|
|
| | AI-Powered Apps Are Changing the Dynamic Between Domain Experts and Developers (dbreunig.com) |
|
1 point by dbreunig 30 days ago | past
|
|
| | AI Chatbots Are Like Observational Comics (dbreunig.com) |
|
1 point by dbreunig 32 days ago | past
|
|
| | ChatGPT fixes your DALL-E prompt if it's bad, but lets it be if it's good (dbreunig.com) |
|
2 points by dbreunig 54 days ago | past
|
|
| | Controlling FFmpeg with natural language from the command line (dbreunig.com) |
|
3 points by dbreunig 75 days ago | past
|
|
| | A Gentle Guide to Running a Local LLM, for Complete Beginners (dbreunig.com) |
|
7 points by dbreunig 3 months ago | past
|
|
| | DeepSeek Is a Rorschach Test Revealing Each's AI Hopes and Fears (dbreunig.com) |
|
1 point by dbreunig 3 months ago | past
|
|
| | The Rise of the Term "Authentic Data" Illustrates AI Anxiety (dbreunig.com) |
|
4 points by dbreunig 3 months ago | past | 1 comment
|
|
| | Eval Is More Important Than the Model (dbreunig.com) |
|
4 points by onel 3 months ago | past
|
|
| | Your Eval Is More Important Than the Model: Building an Example Eval (dbreunig.com) |
|
1 point by dbreunig 4 months ago | past
|
|
| | The "Cyren" Song: Meta's AI profiles, Character.ai, and other fake humans (dbreunig.com) |
|
2 points by dbreunig 4 months ago | past
|
|
| | A Primer on Synthetic Data: How It's Helping and Shaping LLMs (dbreunig.com) |
|
1 point by dbreunig 4 months ago | past
|
|
| | Pipelines and Prompt Optimization with DSPy (dbreunig.com) |
|
1 point by sebg 4 months ago | past
|
|
| | DSPy Does the Prompting for You (dbreunig.com) |
|
2 points by dbreunig 4 months ago | past
|
|
| | An orchestration of small, specialized models might the next breakthrough (dbreunig.com) |
|
1 point by rtusiime 5 months ago | past | 1 comment
|
|
| | LLMs Hit the Wall: History Reveals How We Went Fast and Why We'll Go Slow (dbreunig.com) |
|
2 points by dbreunig 5 months ago | past
|
|
| | Turning Your Root URL into a DuckDB Remote Database (dbreunig.com) |
|
4 points by ulrischa 5 months ago | past
|
|
| | Detecting DuckDB Requests in Your Webapp to Route Them to Remote DBs (dbreunig.com) |
|
3 points by dbreunig 5 months ago | past
|
|
| | Surging crypto prices dampened interest in AI in 2020. Will they do it again? (dbreunig.com) |
|
1 point by dbreunig 5 months ago | past
|
|
| | Transitioning from the attention era to the automation era (dbreunig.com) |
|
10 points by dbreunig 5 months ago | past | 2 comments
|
|
| | Generating Descriptive Weather Reports with LLMs (dbreunig.com) |
|
2 points by freediver 6 months ago | past
|
|
| | It's the UX, Not the LLM: ChatGPT and Perplexity Can Ship a UI Google Can't (dbreunig.com) |
|
3 points by dbreunig 6 months ago | past
|
|
| | Generating Descriptive Weather Reports with LLMs (dbreunig.com) |
|
1 point by dbreunig 6 months ago | past
|
|
| | The 3 AI Use Cases: Gods, Interns, and Cogs (dbreunig.com) |
|
4 points by yarapavan 6 months ago | past | 1 comment
|
|
| | AI Use Cases: Gods, Interns, and Cogs (dbreunig.com) |
|
2 points by thunderbong 6 months ago | past
|
|
| | AI Use Cases: Gods, Interns, & Cogs (dbreunig.com) |
|
4 points by dbreunig 6 months ago | past
|
|
| | Wikidata Is a Giant Crosswalk File (dbreunig.com) |
|
57 points by janvdberg 7 months ago | past | 2 comments
|
|
| | Wikidata as a Giant Crosswalk File (dbreunig.com) |
|
96 points by dbreunig 7 months ago | past | 9 comments
|
|
|
|
More |
