I sometimes have to decide between running Claude Code headless with a prompt or let CC generate an application based on the prompt. (coining: Codification Threshold tradeoff)
The tradeoff is that the prompt is non-deterministic, but also more flexible. It can handle unknown situations. The generated code executes much faster and reliable for known situations.
If auto-learn would reduce the non-deterministic nature, i.e. chance of failing, that would speed up software development.
The person in the Cursor platform is raising a different question and a valid one. We have tons of these frameworks out there, openspec, amplifier, etc. The ultimate dream is to have these subagents work in the background autonomously.
However reality tells us that you constantly have to keep Claude on the right track. Nudge here, nudge there. Close code reviews. Test, test more. Very interactive. Superpowers to the engineer.
It is this contradiction that also makes me believe that it will take another year for agents to work on enterprise codebases autonomously. Maybe more, look at autonomous self driving, surprisingly hard to get to the last 10%.
I think this is the challenge and the dissonance. For something to truly run autonomously you need to provide it some many constraints that it almost loses its usefulness. I've tried using AI, or at least looked into what I could use AI for to automate marketing tasks and I just don't think I can seriously set up a workflow in n8n or AgentKit that would produce sufficiently good results without me jumping in. That said, AI is incredibly helpful in this semi-autonomous mode with the right parameters, to the point of the parent comment.
Moreover they’re not even that great as a search tool. Often just giving incorrect or outdated synthesized results. Marginally better than a raw google search because I can skip all the sponsored/SEO hack results with garbage info.
It is just a new way of coding. And indeed what the blog post said, if you are experienced, you will benefit the most as the AI agent will make similar mistakes as a junior and you will be able to recognize them.
But indeed, the fun part of coding a couple of routines is gone. That is history.
ChatGPT’s generic search will not be that good compared to apps specialized in this.
I tried buying a special kind of lamp this weekend, all LLMs and google sucked at this. The conversation did not help in finding more fine grained results.
True, you need to instruct the AI agents to include this.
In our case the agent has access to Jira and has wider knowledge. For commit messages i don’t bother that much anymore (i realise typing this), but for the MRs I do. Here i have to instruct it to remove implementation details.
> you need to instruct the AI agents to include this.
The agent can't do that if you told Claudepilotemini directly to make some change without telling it why you were prompting it to make such a change. LLMs might appear magic, but they aren't (yet) psychic.
He's saying that he likely has an MCP connected to jira on the LLM he's developing with.
Hence the prompt will have already referenced the jira ticket, which will include the why - and if not, you've got a different issue.
Now the LLM will only need something like "before committing, check the jira ticket we're working on and create a commit message ...
But whether you actually want that is a different story. You're off the opinion it's useful, I'd say it's rarely doing to be valuable, because requirements change, making this point in time rational mostly interesting in an academic sense, but not actually valuable for the development you're doing
It depends on a ton of factors, and at least I'd put very little stock in the validity of the commit message that it might as well not exist. (And this is from the perspective of human written ones, not AI)
The tradeoff is that the prompt is non-deterministic, but also more flexible. It can handle unknown situations. The generated code executes much faster and reliable for known situations.
If auto-learn would reduce the non-deterministic nature, i.e. chance of failing, that would speed up software development.
reply