Michael Mizner

WebDev ➤ Agentic AI Engineering

[Michael Mizner @michaelmizner]

@opencode

[Michael Mizner @michaelmizner]

@icreatelife apply_patch

[Michael Mizner @michaelmizner]

@sflorimm

[Michael Mizner @michaelmizner]

@photomatt Hear me out

[Michael Mizner @michaelmizner]

@photomatt @DeveloperSteve @photomatt I can't see the path clearly – but I think WordPress specifically has a way to navigate this. It's going to get weird, but I'm rooting for you.

[Michael Mizner @michaelmizner]

@rezoundous Chuck Norris apparently

[Michael Mizner @michaelmizner]

@PaulSolt Created a "Codex Plan" skill that Opus uses. Optimizes for Codex coding.

[Uncle Bob Martin @unclebobmartin]

For all the hype and hullabaloo about AI and vibe coding; this is not a layman's domain. The engineering bar is going way up, and getting over that bar will not be easy.

[Michael Mizner @michaelmizner]

@q_yeon_gyu_kim Sorry, had to do it anyways

[Sisyphus Labs @justsisyphus]

now we have https://t.co/W4z7OrBPQ9 for oh-my-opencode

finally with proper docs

[Michael Mizner @michaelmizner]

You should try @finnatsea's Aqua Voice (https://t.co/5DhF8bJL0z). One month in, and I barely type anymore. My favorite product in years.

[Uncle Bob Martin @unclebobmartin]

I do not feel like I'm not programming. In fact, I feel like I am programming more intensely than ever. I'm just not coding.

[Lex Fridman @lexfridman]

Programming is now 10x more fun with AI.

[Michael Mizner @michaelmizner]

AI coding tools are speeding up the process at lightning speed – but real market strategy is needed.

[Paul Mit @pmitu]

If you think building is hard, try getting the first 10 users.

[Theo - t3.gg @theo]

We got him

[Michael Mizner @michaelmizner]

It's hard to argue with — the landscape is shifting quickly.

[Ashutosh Maheshwari @asmah2107]

Multi-agent workflows are the future.

Adapt or perish.

[Michael Mizner @michaelmizner]

Very promising for practical orchestration for engineer guided agents.

[Visual Studio Code @code]

You told us you’re running multiple AI agents and wanted a better UX. We listened and shipped it!

Here’s what’s new in the latest @code release:

🗂️ Unified agent sessions workspace for local, background, and cloud agents
💻 Claude and Codex support for local and cloud agents
🔀 Parallel subagents
🌐 Integrated browser
And more...

[Michael Mizner @michaelmizner]

OpenAI is targeting creators in a way I haven’t seen since Apple in the early 2000’s

[OpenAI Developers @OpenAIDevs]

GPT-5.2 and GPT-5.2-Codex are now 40% faster.

We have optimized our inference stack for all API customers.

Same model. Same weights. Lower latency.

[Michael Mizner @michaelmizner]

@opencode's LSP handles this well: feeds the model full structured context (diagnostics, navigation, types) via pyright/gopls/etc.

Night-and-day difference IMO. Highly recommend.
https://t.co/N34gULhZzB

[BURKOV @burkov]

Claude is great at coding. Like really, really good, compared to using a regular LLM like Gemini.

There's only one issue with it. Because it never sees the full code of the app but uses grep search for relevant code snippets, it's myopic.

If grep returns a fragment of code similar to the bug description, it often doesn't look further and fixes an irrelevant part of the app or answers a question based on these fragments found by grep.

So, as the codebase grows, it becomes important for the user to know the codebase. Otherwise, Claude will reinvent the bicycle over and over again, creating duplicate implementations for the same functionalities in different places in the app.

This issue is probably fixable with additional finetuning, but right now this is how it works.

[Michael Mizner @michaelmizner]

Preparing apply_patch...