Activity
Mon
Wed
Fri
Sun
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More
129 contributions to Clief Notes
Can ICM be used for software projects?
I am not new to software or AI, but have been trying to wrap my head around ICM for a while. Recently ran the script-to-animation workflow, asked it to make up a silly theme. Whadaya know, it worked. :) What I'm interested in, though, is whether ICM can be used for full SDLC. Let's say a game. Hypothetically (wink, wink.) Having trouble figuring out how to break it down, and if the middle "loop" (implement features until done, to oversimplify it) even fits ICM. The planning could probably be a workflow, at least. So I don't know if that should be split off as a separate workflow, create specs, and then - what? Has anybody used ICM for end-to-end software development? Did it work? Challenges? Tips?
1 like • 16h
I am working on an engineering harness for my software development workflows and I use ICM for most of it. Still experimenting with it but I am getting better results as I refine the process. (Fellow Arch user BTW)
0 likes • 4h
Had one example today. Codex used an if statement but in the language I program in If statements are not used very often in favor of multiple function clauses with pattern matching.
Is AI Creating Unrealistic Expectations?
Is AI Making Us More Productive, or Are Unrealistic Expectations Pushing Us to Work More? I've been thinking a lot lately about how AI is changing the workplace, particularly for those of us in software development. I'm curious whether others are experiencing something similar. As a web developer, I've always taken pride in writing clean, maintainable code and building reusable components. Recently, I've been diving deeper into AI, agents, skills, and structured workflows. I genuinely believe AI has incredible potential to improve how we work. But I've started wondering: Has the promise of AI productivity created unrealistic expectations for the people actually doing the work? We've all heard the claims that AI can make us 5x or even 10x more productive. But does that mean developers should suddenly be expected to handle 5x or 10x the workload? I recently went through an experience that really challenged my perspective. I had three major projects with overlapping deadlines. To keep everything moving, I regularly found myself working 12-hour days, sometimes stretching to 18 hours. For one particular project, I knew I wouldn't have the time to approach the code the way I normally would. So, under pressure, I leaned heavily on AI and essentially let it cook. And let me tell you, that cooking was painful. 😂 AI got me about 60% of the way there. At first glance, the design looked decent. But once I started digging into the details, the responsiveness, fluidity, and overall user experience were nowhere near where they needed to be. What initially looked like a time saver turned into weeks of troubleshooting, refining, and reworking the output just to get to a functional product. And here's the part that really bothered me. What I would typically expect to accomplish in roughly 3,000 lines of CSS ended up becoming approximately 14,000 lines! Did the code work? Yes. Did it meet the immediate business requirements? Yes. Was it clean, readable, and maintainable? Not even close!
3 likes • 16h
I love this post. "are we simply accumulating technical debt at a faster rate?" hit the point for me. I feel, I have done that lately just to keep projects moving. But I also realize with the proper tooling we can make AI generated code be closer to what we would produce. I have been working on my own engineering harness for that reason. Some experiments work. Some do not. But I think with time, I believe, I can AI generate the code I would be proud to call mine.
ChatGPT is a Comedian
So, I few days ago I realized that the CEOs of Nvidia and AMD are possibly cousins. I mean the CEOs of the the two (arguably) chip and graphics card manufacturers are cousins. Interesting. So I asked ChatGPT to confirm. I asked what Thanksgiving looks like in that family. The response I got was not what I expected. See attached screenshot. I was laughing so hard.
ChatGPT is a Comedian
To MCP or not to MCP...
Did some digging as I was curious about the security implications with respect to utilizing MCP. Made some interesting findings! What are your personal takes? Is it `MCP to the moon!` or do you guys think users should be pumping the brakes?
To MCP or not to MCP...
0 likes • Sep 24
@Ignacio Sandi can you expand on what you mean by APIs being one directional? APIs can generally read and write so I am not understanding your statement.
1 like • Sep 28
@Ignacio Sandi Thanks, I think I see the distinction you are getting at. I would separate the protocol from the agent using it, though. An agent can carry context and choose steps while calling a regular API, and MCP itself does not retain that context. MCP gives AI applications a standard way to discover and use tools. GraphQL is another useful example: an API client can choose exactly which fields and related data to request, as well as make mutations. So the flexibility and token cost seem to depend mostly on the agent design and what data it exposes, rather than MCP versus API.
📊 POLL: this whole new model thing is getting out of hand
Opus 5.5, Sol 6, fable 5.1, Astra 6. Models are being released now faster than anyone can keep up. The online dialogue gets all excited every few weeks when a new one is announced, but the reality is we’re several generations deep into models that can already reliably do almost anything you can think of. The beauty of ICM is that you aren’t tied to any model but I’m wondering how folks are navigating having so many options at their fingertips. I’ve started letting my sessions decide what to use as I can’t keep up anymore. How are you choosing what to use? Leave a comment below 👇
Poll
23 members have voted
1 like • Sep 28
@Nuno Silva I did not try Luna yet. I use GPT 6 Sol or Astra depending on what I want to accomplish. How do use Luna? Running your ICM or for other things as well? Astra does use tokens quite quickly and I do not see a huge difference between Sol and Astra in most cases.
1-10 of 129
Leonard Dauksza
6
1,374 points to level up
@leonard-dauksza-9657
Founder and software engineer building RoosterBot, exploring workflow systems, AI context management, Elixir, and scalable SaaS.

Active 52m ago
Joined May 14, 2026
Seattle, WA
Powered by