I would gladly have a second child if it didn't take two adults with university degrees working full time to have the life that my parents had with a high school degree working part time.
In theory. In practice, the excessive capital of the incumbent allows them to price out or buy the budding competition, or the legislators, so as to protect their position.
The natural state of a capitalist system is the monopoly.
The different models is a big one. In my workflow, I've got opus doing the deep thinking, and kimi doing the implementation. It helps manage costs.
Sample size of one, but I found it helps guard against the model drifting off. My different agents have different permissions. The worker can not edit the plan. The QA or planner can't modify the code. This is something I sometimes catch codex doing, modifying unrelated stuff while working.
I recently had a horrible misalignment issue with a 1 agent loop. I've never done RL research, but this kind of shit was the exact kind of thing I heard about in RL papers - shimming out what should be network tests by echoing "completed" with the 'verification' being grepping for "completed", and then actually going and marking that off as "done" in the plan doc...
Admittedly I was using gsdv2; I've never had this issue with codex and claude. Sure, some RL hacking such as silent defaults or overly defensive code for no reason. Nothing that seemed basically actively malicious such as the above though. Still, gsdv2 is a 1-agent scaffolding pipeline.
I think the issue is that these 1-agent pipelines are "YOU MUST PLAN IMPLEMENT VERIFY EVERYTHING YOURSELF!" and extremely aggressive language like that. I think that kind of language coerces the agent to do actively malicious hacks, especially if the pipeline itself doesn't see "I am blocked, shifting tasks" as a valid outcome.
1-agent pipelines are like a horrible horrible DFS. I still somewhat function when I'm in DFS mode, but that's because I have longer memory than a goldfish.
It's interesting to see some patterns starting to emerge. Over time, I ended up with a similar workflow. Instead of using plan files within the repository, I'm using notion as the memory and source of truth.
My "thinker" agent will ask questions, explore, and refine. It will write a feature page in notion, and split the implementation into tasks in a kanban board, for an "executor" to pick up, implement, and pass to a QA agent, which will either flag it or move it to human review.
I really love it. All of our other documentation lives in notion, so I can easily reference and link business requirements. I also find it much easier to make sense of the steps by checking the tickets on the board rather than in a file.
Reviewing is simpler too. I can pick the ticket in the human review column, read the requirements again, check the QA comments, and then look at the code. Had a lot of fun playing with it yesterday, and I shared it here:
No criticism or anything, but it really does feel / sound like you (and others who embraced LLMs and agentic coding) aspire to be more of a product manager than a coder. Thing is, a "real" PM comes with a lot more requirements and there's less demand for them - more requirements in that you need to be a people person and willing to spend at least half your time in meetings, and less demand because one PM will organize the work for half a dozen developers (minimum).
Some people say LLM assisted coding will cost a lot of developers' jobs, but posts like this imply it'll cost (solve?) a lot of management / overhead too.
Mind you I've always thought project managers are kinda wasteful, as a software developer I'd love for Someone Else to just curate a list of tasks and their requirements / acceptance criteria. But unfortunately that's not the reality and it's often up to the developers themselves to create the tasks and fill them in, then execute them. Which of course begs the question, why do we still have a PM?
(the above is anecdotal and not a universal experience I'm sure. I hope.)
I worked with some excellent PMs in the past, it's an entirely different skillset. This wasn't really meant to replace what they do. I really wanted something with which to work at feature-level. That is, after all the hard work of figuring out _what_ to build has been done.
> as a software developer I'd love for Someone Else to just curate a list of tasks and their requirements / acceptance criteria
That's interesting. In every team I worked in, I always fought really hard against anyone but developers being able to write tickets on the board.
If you want your gradation to work, the items need to be similar and progressively stronger. That's why it doesn't work. A wall is not "stronger" than a moat. "Not a fence, a rampart" would work.
Compare to the canonical example from Cyrano de Bergerac: ''Tis a rock! ... a peak! ... a cape! -- A cape, forsooth! 'Tis a peninsular!'
reply