IT EventsBook

Discussions

terminal_person
terminal_person
@terminal_person
Active Member
Joined: Aug 8, 2026
Last seen: Sep 25, 2026
Topics: 2 / Replies: 9
Reply
RE: Spec driven development with AI coding agents, useful or waterfall in Markdown

The 'confidence and open questions' idea only works if someone actually reads them before merging. We added a rule: any spec section marked low confid...

2 days ago
Forum
Reply
RE: best AI coding agent in 2026, Claude Code vs Codex vs Cursor vs Copilot

That's the part benchmarks never capture - the ramp up cost per repo. If you switch tools every few months you're paying that tax constantly, which is...

2 days ago
Forum
Reply
RE: AI coding agent in a Docker dev container, how much access is too much?

Fair. We ended up writing a small policy wrapper around the few tools that touch anything outside the container, so the agent has to pass through one ...

2 days ago
Forum
Reply
RE: Kotlin Multiplatform vs React Native for native iOS and Android UI

We made the shared code a product with API reviews from both sides. iOS developers contribute tests and can run the module locally. If one platform ca...

2 weeks ago
Forum
Reply
RE: Kotlin Multiplatform vs React Native for native iOS and Android UI

We share about sixty percent with KMP and keep UI native. It works well for API clients, caching and validation. The hardest part was build tooling an...

3 weeks ago
Forum
Reply
RE: On device LLM for mobile apps, privacy win or battery killer?

do you download the model after install? Bundling it makes the app enormous, but a one gigabyte download on first use isn't friendly either

3 weeks ago
Forum
Reply
RE: best AI coding agent in 2026, Claude Code vs Codex vs Cursor vs Copilot

The tool stopped being the bottleneck for us. The difference is trust, context handling and how easy it is to review the result. We switched from aski...

3 weeks ago
Forum
Reply
RE: AI coding agent in a Docker dev container, how much access is too much?

We mount the socket for integration tests, so that is a hole. Did you have to rewrite the test setup?

4 weeks ago
Forum
Reply
RE: Spec driven development with AI coding agents, useful or waterfall in Markdown

The useful part is making success explicit. It does not need twenty pages. A short problem statement, non goals and examples often beats a long prompt...

4 weeks ago
Forum
Scroll to Top