I wonder if it has anything to do with Anthropic eagerly embracing vibe coding.

Comments URL: https://news.ycombinator.com/item?id=48126435

Points: 9

# Comments: 12

I haven’t used libretto myself yet but I’m excited about having this kind of tool at my disposal as it’s been a need in the past.

EDIT: To clarify, I realize there are skill files that can be used with Claude directly, but the snapshot analysis model seems to require a key. Any way to route that effort through Claude Code itself, such as for example exporting the raw snapshot to a file and instructing Claude Code to use a built-in subagent instead?

OP: if you thought you had something useful to say, why didn’t you write it in your own words. There’s no useful content I can discern while reading this post.

Comments URL: https://news.ycombinator.com/item?id=46897544

Points: 6

# Comments: 2

I feel that we continue to miss the forest for the trees. Writing (or generating) a million lines of code in Rust should not count as an achievement in and of itself. What matters is whether those lines build, function as expected (especially in edge cases) and perform decently. As far as I can tell, AI has not been demonstrated to be useful yet at those three things.

Is there real evidence, beyond hype, that agentic coding produces net-positive results? If any of you have actually got it to work, could you share (in detail) how you did it?

By "getting it to work" I mean: * creating more value than technical debt, and * producing code that’s structurally sound enough for someone responsible for the architecture to sign off on.

Lately I’ve seen a push toward minimal or nonexistent code review, with the claim that we should move from “validating architecture” to “validating behavior.” In practice, this seems to mean: don’t look at the code; if tests and CI pass, ship it. I can’t see how this holds up long-term. My expectation is that you end up with "spaghetti" code that works on the happy path but accumulates subtle, hard-to-debug failures over time.

When I tried using Codex on my existing codebases, with or without guardrails, half of my time went into fixing the subtle mistakes it made or the duplication it introduced.

Last weekend I tried building an iOS app for pet feeding reminders from scratch. I instructed Codex to research and propose an architectural blueprint for SwiftUI first. Then, I worked with it to write a spec describing what should be implemented and how.

The first implementation pass was surprisingly good, although it had a number of bugs. Things went downhill fast, however. I spent the rest of my weekend getting Codex to make things work, fix bugs without introducing new ones, and research best practices instead of making stuff up. Although I made it record new guidelines and guardrails as I found them, things didn't improve. In the end I just gave up.

I personally can't accept shipping unreviewed code. It feels wrong. The product has to work, but the code must also be high-quality.

Comments URL: https://news.ycombinator.com/item?id=46691243

Points: 461

# Comments: 455

* Codex's built-in web search tool: can't browse JS-only sites. In my case, it's unable to browse developer.apple.com. * `microsoft/playwright-mcp`: It's able to perform searches and read pages, but very heavy hit on context. Burned through 10% of the context window for a single search. * Exa.ai, context7.com, Brave Search MCP: I'm strongly turned off by the pay-per-thousand model or caps on free plans. I understand they have to make money, it's just not what I want to spend money on. * https://github.com/arabold/docs-mcp-server: I didn't test this, but I was turned off by the fact you have to run the server in the background instead of allowing it to be booted by the Codex instance (via npx) like it can for other kinds of MCP servers.

Does anyone have a solution to this that hits on all marks: free, able to read websites including JS ones, thorough and high-quality?

Comments URL: https://news.ycombinator.com/item?id=46657082

Points: 1

# Comments: 2

Comments URL: https://news.ycombinator.com/item?id=46310891

Points: 2

# Comments: 0

I’ve heard Opus 4.5 might be better for coding. SWE-bench shows an 8% improvement but I'm having a hard time guessing what kind of effect that maps to in reality. For those who’ve switched, what changes have you seen, and how has it affected your work? Is the $100/month upgrade worth it?

Comments URL: https://news.ycombinator.com/item?id=46288517

Points: 5

# Comments: 6

In my opinion it’s about your ethical stance and who your target audience is, and whether you’re trying to make a ton of money or just enough to survive. You’re obviously going to fight an uphill battle if you don’t employ any such (predatory?) marketing tactics. However, you could position yourself as explicitly standing against those and that might attract a smaller but loyal user base.

If you’re lucky, and build something good, and people talk about it, you might find that you’ll get users regardless. However, at the end of the day, what matters is whether you can keep the lights on, so you may have to relax some of your stances and rules or find ways to market your product that don’t fall into the categories you’ve described.