andyk
- Karma
- 251
- Created
- August 18, 2012 (13y ago)
- Submissions
- 0
- #1 agent on swe-bench wrote 7% of its own code (aider.chat)
- AI benchmarks should be like unit tests (andykonwinski.com)
- OpenAI Dropped Work on New 'Arrakis' AI Model in Rare Setback (theinformation.com)
- The HTTP QUERY Method specification (httpwg.org)
- Show HN: Recursive LLM Prompts (github.com)
I've been playing with the idea of an LLM prompt that causes the model to generate and return a new prompt. https://github.com/andyk/recursive_llm The idea I'm starting with is to implement recursion using English as…
- Show HN: Natural language Twitter search using Codex (perplexity.ai)
We built a structured search engine for Twitter called Bird SQL, available at https://www.perplexity.ai/sql. Our search interface uses OpenAI Codex to translate natural language to SQL. Our backend then verifies the…
- Tips for self-study and independent research (andykonwinski.com)
- Free live stream of 1st Apache Spark Big Data Summit Dec 2-3 (spark-summit.org)
- 1st Apache Spark Summit agenda posted, 18 talks by edu & biz (spark-summit.org)
- The UC Berkeley Big Data AMP Camp, August 29-30 (ampcamp.berkeley.edu)
- AMP Camp 3 Big Data Bootcamp (ampcamp.berkeley.edu)