Joe Muoio

Full stack freelance software developer and consultant building AI integrations and Cloud services. I like games and food.

[Joe Muoio @JoeMoCode]

Maybe 4.8 is "better" at coding, but I will just start trying it for planning for now. I'd much rather use a cheap model for implementation than an expensive one.

Big context window and better natural language processing is useful when researching and planning, not coding.

[Joe Muoio @JoeMoCode]

Opus 4.8 is out, but I am WAY more hyped about Composer 2.5 for coding.

Opus class has been good for planning... but it's somehow worse at coding than composer. By the time I code with AI, the task is well thought through and I just need it done.

[Joe Muoio @JoeMoCode]

@plainionist yeah totally there is a place for rules. I see them primarily as a way to direct agent to the place it needs to find that info rather than capturing it in a likely duplicate way. I don't give agents roles like that so I don't have opinions on that, specifically.

[Joe Muoio @JoeMoCode]

@sickdotdev 100% Cursor

Vertically integrated harness has most potential, but also most risk when the company is built to sell compute

VSCode (with devcontainers) + Cursor CLI for in the loop dev.

Cursor Cloud agents for parallelized sessions.

Cursor IDE is not my cup of tea

[Joe Muoio @JoeMoCode]

https://t.co/3lDqAuTlVB

Matt's skills are great. At least the few I have used, so far. Lots of good stuff in here I have not even discovered yet, I am sure.

[Matt Pocock @mattpocockuk]

Skills should be:

- Concise
- Responsible for one thing, not multi-step
- Composable
- Progressively disclosed
- Harness-agnostic

What else? Or - what did I get wrong?

[Joe Muoio @JoeMoCode]

@plainionist not everything is so simple, but there are some things that are :)

Rules are always gonna be "okay-ish" and never going to SOLVE a problem. Only mitigate how often it happens.

[Joe Muoio @JoeMoCode]

@plainionist That's insulting to the goldfish who do actually have memory!

Shift away from rules to determinism.

Example, don't have rules about code style, instead have a hook that runs your linter and hook that up to run when a file is changed by your AI harness. No need for style rules

[Joe Muoio @JoeMoCode]

@DanielMiessler @MattTrifilo And this is a core assumption of the argument. That we have "intelligence". I like that you defined it here and agree models give us this to an extent.

Employees also give accountability. How okay is it if the workflow is wrong? who has accountability?

Bigger problem, IMO

[Joe Muoio @JoeMoCode]

@thdxr I been thinking this as well... but, don't forget about your own skill growth in that time!

Turns out things are hard. Software is hard, and we are here and like it because it is hard. Always something new to learn and apply.

[Joe Muoio @JoeMoCode]

Only if the practitioner wants better software and knows what that means and what it takes.

Lots of examples to the contrary -- more bad software getting made than ever before.

More great software being made as well.

...just more software getting made. :)

[Seb @plainionist]

Before AI, software development felt like:

10% design - 80% coding - 10% testing

With AI, it became more like:

40% design - 20% prompting - 40% testing

More thinking.
More verification.

So ... better software? 🤔

[Joe Muoio @JoeMoCode]

@plainionist huh, that's a very interesting tool... 🤔🤔🤔

[Joe Muoio @JoeMoCode]

@plainionist DSL needs to REALLY show value for it to be adopted and used to the point that we then fine tune models on it at scale. Without that, you are locking yourself in and/or the model will have minimal knowledge of it, or will have to bloat context to share knowledge of DSL.

[Joe Muoio @JoeMoCode]

@plainionist For runtime use cases with claude for instance, I use XML in order to better separate parts. Recommended in claude docs, too.

I don't use it for general plans/notes/research and still opt for md. Kinda since its the default format and I haven't felt the need yet to change.

[Joe Muoio @JoeMoCode]

Clarity is good.

Changing how your tool works in a way that is not technically sound and breaks the work folks who love building on your tech and pushing subscriptions is exactly the reason why I left Anthropic behind months back.

Big miss from Anthropic in a year of misses.

[ClaudeDevs @ClaudeDevs]

Starting June 15, paid Claude plans can claim a dedicated monthly credit for programmatic usage.

The credit covers usage of:
- Claude Agent SDK
- claude -p
- Claude Code GitHub Actions
- Third-party apps built on the Agent SDK

[Joe Muoio @JoeMoCode]

@nbaschez Same problem we always had as devs with analysis paralysis.

The point of the plan and doc is to think through the problem. So you are done when you have done that and have a sufficiently detailed written plan you approve of.

[Joe Muoio @JoeMoCode]

@trashh_dev If you ain't using 1 trillion dollars of tokens per month are you even a senior dev?!

[Joe Muoio @JoeMoCode]

@kareem_carr Super well said! This is also why it works great for Programming, too, of course. Even tighter validation loop.

And exactly why all the weirdos thinking you need to track your prompts for software dev are totally off base. Code >>> fuzzy human language.

[Joe Muoio @JoeMoCode]

@johncrickett I mean I think you nailed it. Curiosity and skepticism. What actually works and why you choose certain tools and techniques. How you integrate with a team.