After over a year of frenetic fun coding using agents, I finally miss the calm and deep immersion of working on a complex task on my own. This is not to say that I don’t want to use agents anymore, or that I want to return to the earlier way of working. I’m just surprised at feeling this sense of nostalgia, since I’ve had zero issues so far transitioning to working through agents and still feeling the sense of “agency”.
Experimented with a barebones agent that forced the model to reply only in Python, and then automatically executed the generated python. I tried it with Qwen-2.5-Coder, Gemma4 E4B, and Qwen3-4B-Instruct. The idea was to remove the need for a bash/powershell tool, and have the agent write complex tool call chains in a single program output. The first approach extracted python code blocks from the reply and executed them. The second approach exposed python as a regular tool.
The models powering coding agents currently feel more like fuzzy function calls, or Q&A bots. For more complex tasks, it would be better if they (ironically) behave more like chat, where they refine their understanding (and mine too) with follow-up questions and discussion, rather than being biased towards “answering”/“solving” in the very next reply. For e.g. when talking to a freelancer, we’d expect them to ask follow-up questions and clarify the requirements until we’re both sure that we’ve really understood the task. Or maybe even clarify stuff while implementing. “Plan mode” is an okay approximation (especially if you explicitly ask it to list questions for me). But that’s a workaround - the model is not explicitly post-trained/architected for dialogue. And doesn’t come into play during implementation.