On Wednesday, @solana introduced Solana Bench, for testing AI’s ability to generate Solana transactions. The verdict: it’s pretty good for things like core Solana transactions & Jupiter swaps. So we decided to show you how you can make it effortless for LLMs like Claude Code to generate transactions across dozens of more complex DeFi actions. TL;DR—Blinks are APIs for transactions, which are so much easier to use than SDKs. And that’s good for LLMs (& humans)
How well can LLMs actually build transactions on Solana? Until now, there wasn’t a simple, reproducible way to measure. Introducing Solana Bench — open benchmarks for testing AI’s operational competence on Solana. Mega-thread 🧵
3,753
0
本頁面內容由第三方提供。除非另有說明,OKX 不是所引用文章的作者,也不對此類材料主張任何版權。該內容僅供參考,並不代表 OKX 觀點,不作為任何形式的認可,也不應被視為投資建議或購買或出售數字資產的招攬。在使用生成式人工智能提供摘要或其他信息的情況下,此類人工智能生成的內容可能不準確或不一致。請閱讀鏈接文章,瞭解更多詳情和信息。OKX 不對第三方網站上的內容負責。包含穩定幣、NFTs 等在內的數字資產涉及較高程度的風險,其價值可能會產生較大波動。請根據自身財務狀況,仔細考慮交易或持有數字資產是否適合您。