> Coding agents are designed to be accommodating, it doesn’t push back against prompts since it neither has the authority nor the context to do so. It may ask for clarifications upon what was specified, but it won’t say “wait, have you considered doing X instead?” A human developer would, or at least, they’d raise a flag. An LLM produces plausible output and moves on.
> This trait may be desirable as a virtual assistant, but it makes for a bad engineering teammate. The willingness to engage in productive conflict is part and parcel to good engineering: it helps broaden the search in the design space of ideas.
Whenever non-technical people ask me about LLMs, I tell them this -
The goal of an LLM is not to give you correct answers. The goal of an LLM is to continue the conversation.
If you select Search > Advanced from the menu, you get a window where you can enter the content to search for. This is available in the normal as well as the alpha version.
> Last week Cursor published Scaling long-running autonomous coding, an article describing their research efforts into coordinating large numbers of autonomous coding agents. One of the projects mentioned in the article was FastRender, a web browser they built from scratch using their agent swarms. I wanted to learn more so I asked Wilson Lin, the engineer behind FastRender, if we could record a conversation about the project. That 47 minute video is now available on YouTube. I’ve included some of the highlights below.
The parent comment shows two rows of different types - the upper row consists of the taskbar, and the lower row has the quick launch icons, drive links, and a music bar.
It's not. You can add quick launch icons and drive shortcuts natively (right click > Toolbars > New Toolbar). I only use Taskbar Tweaker to replace the Windows Aero-style tooltip with the standard jump list right click menu.
The media taskbar player can be added natively from older versions of iTunes, Windows Media Player, or others.
The title accurately describes what happened without any sense of editorial sensationalism. The title doesn’t match word for word with what the original had but that’s not even close to the same thing you’re complaining about.
> Coding agents are designed to be accommodating, it doesn’t push back against prompts since it neither has the authority nor the context to do so. It may ask for clarifications upon what was specified, but it won’t say “wait, have you considered doing X instead?” A human developer would, or at least, they’d raise a flag. An LLM produces plausible output and moves on.
> This trait may be desirable as a virtual assistant, but it makes for a bad engineering teammate. The willingness to engage in productive conflict is part and parcel to good engineering: it helps broaden the search in the design space of ideas.
Whenever non-technical people ask me about LLMs, I tell them this - The goal of an LLM is not to give you correct answers. The goal of an LLM is to continue the conversation.
reply