Following on from my previous post [https://mastodon.social/@arsalan_zaidi/116945759256450237/embed], here's a simple test of these models as coding agents. I had them vibe code a very simple console based program and then run the output and examined it for code quality. I've deliberately kept the prompt simple and 'vibey' to see how the model reacts and what assumptions it makes. Read the thread to see the whole post.🧵 #AI #LLM #LocalLLM #Ollama #VibeCoding #Coding #SoftwareDevelopment
Related
Apple raises prices for Apple Music and Apple One subscriptionsApple has raised the price of Apple Music today in the Un...
Apple raises prices for Apple Music and Apple One subscriptionsApple has raised the price of Apple Music today in the United States and other countries. Starting today, Apple Music...
#AI advice made people 3X less accurate but 2X as confident, researchers foundWillingness to say "I don't know" collapse...
#AI advice made people 3X less accurate but 2X as confident, researchers foundWillingness to say "I don't know" collapsed from 44% to 3% when AI was available. Monetary incentives ...
山田、まだ信頼できませんね米テック5社AI投資、｢見えざる債務｣268兆円 注記のみ記載に危うさ https://www.nikkei.com/article/DGXZQOGN265UU0W6A620C2000000/#Apple #LLM...
山田、まだ信頼できませんね米テック5社AI投資、｢見えざる債務｣268兆円 注記のみ記載に危うさ https://www.nikkei.com/article/DGXZQOGN265UU0W6A620C2000000/#Apple #LLM #news #bot