itmitica

Why make others misfortune a platform for ego expression? Why not doing things elegant, quiet, keep it in-house? Because misery of others drives stock prices up! It's a sacrifice he's willing to make.

I'm sold!

But, what about...

Again, you are building an audit agent.

You just use some theater around it.

For the purpose, the best audit agent is a completely different agent, not a different persona of the same agent.

So, you're saying, build tests? TDD?

I did the exact same thing! Uncanny.

I agree with models being better at different tasks: gemini-cli is superficial, codex is stubborn as a mule and dependable, claude-cli just wants to get something working and done. qwen-cli, Qwen, in general, has a tendency to pendulate too much.

I also reduced the team to two, codex and claude, for me.

... or, maybe, simply use another agent to audit it?

Agent teams sound better than literature-induced confidence.

Are you anthropomorphizing when you should just automate the review?

I appreciate your work.

But, again, from a productivity point of view, and from a correctness of approach point of view, I have learned this:

1. Avoid overengineering against/at all costs.

2. Doing the project is doing the project, anything else is ... not doing the project :) https://www.softwaredesign.ing/blog/doing-the-thing-is-doing...

I like your content very much, let me point this out first.

I'm not sure all aspects are covered in the approach.

For instance, controlling the agents takes a big chunk of the interest. The agentic system architecture is also big in view.

But, the way I see, more important staff is: project structure, coding best practices, testing strategies. All still deterministic. All still very tough to get agentic to do it right.

I think agentic should just be means to an end: project quality and project ease of management. If not, it's just an indulgence that costs money.

I too was convinced at one point the spec is the program.

That it doesn't matter the implementation stack.

But, after wasting too much time in the meta, with nothing really to show for, I returned to controlling the programming process in fine detail. Progressive agentic/vibe coding, if I was to give it a name.

But it could be that I'm slow to understand how it can be done in a better way.

Interesting project.

Interesting readings in the project, such as https://github.com/desplega-ai/advanced-context-engineering-....

I'm not sure why, but I keep trying to reject this, subconsciously. Like, there is something I can't define that is not right.

I think it revolves around two things

No actual future benefits from abandoning the problem solving to a temporary swarm construct that will have a solution ready but potentially having learned nothing from the experience, that could be used in the future.

Shifting the engineering from stable sourcecode and frameworks to ephemeral prompting one-shot-and-done solutions.

Has programming become too meta?

Not really. You just found another way to tell Claude "I want a game, I am uncertain, let's randomly seed the start of the process.". But you did it circus-style :)

Code Mode is a workaround for poor tool packaging.

Instead of improving the MCP ecosystem’s capability discovery model, they reduced context pressure by collapsing the tool ecosystem into a programmable backend.

It’s a vendor-specific, host-opaque, low-observability MCP-exposed programmable API gateway with weak MCP-layer governance semantics.

“We won’t fix the simple, visible server-side problem, so we’ll distribute a harder version of it into every client.”

Flawed. GPT 4.1 gets it right. GPT 4.1 mini answers wrongly. It's about quantization, not about model. The companies clearly cut corners on some inferences, they are quietly using lesser models than advertised or listed in plain sight.

The normal reaction is, there you are, I managed to do this using cli. The gratuitous ragebait way is, there you are, I managed to do this using cli, hence MCP is dead. But why?

În real world, worst performers get thrown out of the loop if they are flagged and fail to improve. Assumption here seems to be agents have no such issues. Am I missing something?

In the real world, over engineering is the play to work-pretend sped money, with more theatre than results. Am I missing something here too? Deep agentic factories? Deepest agentic factories?

All models are trapped in memory in an ephemeral space of time. Agents used to interact with the models make it seem otherwise.

Share and you can't control what everyone else does with the data. Hence, untether is a non concept. In the sense that that data has now lost it's uniqueness. You can untether all you want. Copies of it will be subjected to any kind of tethering and transformation. So, if your point was about control, forget it.

To share is to lose control. You can't undo, even once shared, it can't be undone. You can't retract a published novel. You can't retract a broadcast music or show. What makes you think you can do it over internet?

JSON Schema? https://github.com/rjsf-team/react-jsonschema-form

Is this a bad bait or is it a bad post? I can't decide.

hmmmm....

Seems like the natural thing to do.

Also did that already, offered all but the code and interposed bring-your-own-AI in the process, and seems like a natural convergence.

Yeah, but still not org mode.

Question: why is `https://orgmode.org/` in html and not in ... org mode?

Syntax highlighting gains, regardless of color scheme, are not negligible. There are grayscale color schemes, for example, that remove the violent nature of some color themes.