Building simple tools has never been easier. With GPT-4 + Replit we built a logo finder tool in under 2 minutes. All it took was a single prompt and clicking run.
CODE
-
GPT-4 Closed-Source Value: Boosting Developer Productivity Tenfold
By
–
GPT-4 has awesome value even as a closed-source solution. It provides proof of existence and will motivate other groups. For $20/mo (and some caution), developers can 10x their speed of producing high-quality code.
-
OpenAI Open Sources Evals Framework for GPT-4 Model Evaluation
By
–
Less publicized but highly awesome aspect of GPT-4 launch was that OpenAI open sourced an evals framework, allowing us to crowdsource model evaluations at scale . The repo is getting some very high quality PRs (rewarded with GPT-4 access). I <3 evals; `pip install evals` https://
x.com/kondrich2/stat
/kondrich2/status/1635687409668227072
… -
MVP Speed vs Technical Debt: Architecture Trade-offs
By
–
Best part: all super easy tools to get going with an MVP Worst part: doesn’t require thoughtful architecture to start, so my “tech debt” is up the wazoo
-
Email summarization system with key facts extraction
By
–
People are asking so here's how I did the prior steps… For bullet points extracted from emails, I have a system that creates a "summary of interactions" for every email address. In this, I also extract a list of key facts from every email that I store.
-
GPT-4 as a Multiplier: Amplifying Engineering Capabilities
By
–
GPT-4 should be thought of as a multiplier to your capabilities. If you are a 1x engineer, you can become 10x. If you are a 0x engineer, you will stay at 0 or may even go negative. I just asked GPT-4 to write OpenCV code for Photometric Stereo, and it produced beautiful code.
-
Building Evaluations for Frontier Language Models
By
–
2. Building evaluations. Many benchmarks get quickly saturated, and we need more to evaluate the frontier of language models. In addition, it’s still an open question of how to evaluate language models generally. The new OpenAI evals library could be good: https://
github.com/openai/evals -
MIT Codon Compiler Accelerates Python Code 100x Faster
By
–
MIT researchers recently developed Codon, a Python-based compiler that helps create new DSLs w/i the language. The results: their code runs up to 100 times faster than regular Python. https://
bit.ly/3mRlMtP -
Live Special: Generative AI, ChatGPT and OpenAI Ethics
By
–
Live Special! #GenerativeAI #OpenAI #ChatGPT
— Sen. Sally Eaves (@sallyeaves) 16 mars 2023
🗓️https://t.co/w5q3zTnz1k 🎙️
March 20th @InfosysAusNZ @UNSW @CommBank #DataScience #Analytics @Xbond49 #bias #AI #Python @RLDI_Lamy #100DaysOfCode #AIEthics @sonu_monika #womenintech @DigitalColmer @dinisguarda @CurieuxExplorer pic.twitter.com/aw2iMkrWl1Live Special! #GenerativeAI #OpenAI #ChatGPT http://
bit.ly/AIAfterNext March 20th @InfosysAusNZ @UNSW @CommBank #DataScience #Analytics @Xbond49 #bias #AI #Python @RLDI_Lamy #100DaysOfCode #AIEthics @sonu_monika #womenintech @DigitalColmer @dinisguarda @CurieuxExplorer -
Haskell Becomes Accessible to Non-Math PhDs
By
–
It is finally possible for those without a math PhD to write Haskell: