Last May, I wrote a blog post titled As an Experienced LLM User, I Actually Don’t Use Generative LLMs Often as a contrasting response to the hype around the rising popularity of agentic coding. In that post, I noted that while LLMs are most definitely not useless and they can answer simple coding questions faster than it would take for me to write it myself with sufficient accuracy, agents are a tougher sell: they are unpredictable, expensive, and the hype around it was wildly disproportionate given the results I had seen in personal usage. However, I concluded that I was open to agents if LLMs improved enough such that all my concerns were addressed and agents were more dependable.
Ранее Зеленский в грубой форме отказался выводить украинские подразделения из Донбасса в рамках урегулирования конфликта. Он назвал это «чушью собачей».
，推荐阅读快连下载安装获取更多信息
“We have some really wonderful people who are the old guard that feel like they are the comfortable welders, and they’re all very wise,” he said. “But even in the newest editions, we’re not here because we think that it’s all going to be done within our lifetimes. We like to joke about 2090 and about raising our children to work on the project. We just like to look at the next release, and that tends to be exciting enough to get us going.”
Wordle today: Answer, hints for February 28, 2026