Trail of Bits (🔗Twitter)[🤔➡️🔗🧵⚠️]
RT @charles_irl: Nice insights in this article from @trailofbits on evaluating open & proprietary LLMs for Copilot-style autocompletion in Solidity.
> a larger model quantized to 4-bit quantization is better at code completion than a smaller model of the same variety
https://blog.trailofbits.com/2024/11/19/evaluating-solidity-support-in-ai-coding-assistants/
🌐 Прилетело из @BizFeed
RT @charles_irl: Nice insights in this article from @trailofbits on evaluating open & proprietary LLMs for Copilot-style autocompletion in Solidity.
> a larger model quantized to 4-bit quantization is better at code completion than a smaller model of the same variety
https://blog.trailofbits.com/2024/11/19/evaluating-solidity-support-in-ai-coding-assistants/
🌐 Прилетело из @BizFeed