Viewing profile — skapadia

An agent will read your comment and take it as a challenge to show something can go wrong. Thanks for prompt injecting, mate. /s

This will have significant consequences for the military.

This is beautiful, I can't deny that. But the claim that Claude Code is a fixed set of tools is quite wrong. Claude Code regularly generates new code to carry out tasks, and you ca…

[dead]

Much of the world believed in geocentrism for a very long time, yet we've known better for a long time now. Currently, this "Ptolemaic" idea of human intelligence being the center …

This is awesome. Thank you for pointing out streaming JSON input and output, I'll definitely be taking a look at that.

Basically, as long as you are using an Anthropic library or tool, you can use your OAuth credentials. For example, you can use the Claude Agent SDK with your OAuth credentials. Thi…

The second paragraph sounds eerily AI-generated.

1. playwright-cli for exploration and ad-hoc scraping, in order to determine what works. 2. playwright code generation based on 1, which captures a repeatable workflow 3. agent ski…

"Test harness is everything, if you don't have a way of validating the work, the loop will go stray" This is the most important piece to using AI coding agents. They are truly magi…

"To come back to my earlier comment, though, my main approach makes sense in this context. I let Opus do the abstract thinking, and then OpenAI's models handle the fine details." V…

Thanks, I'll try those out. I've used Codex CLI itself on a few small projects as well, and fired it up on a feature branch where I had it implement the same feature that Claude Co…

Claude Opus 4.5 by far is the most capable development model. I've been using it mainly via Claude Code, and with Cursor. I agree anticompetitive behavior is bad, but the productiv…

Exactly. We're headed for a discontinuity, not an inflection point.

Hey HN! In 2025, I've spent more time than ever conversing with AI coding agents, particularly Claude Code. These conversations are an intimate look into how we think and solve pro…

Exactly. Prompt + Tool + External Dataset (API, file, database, web page, image) is an extremely powerful capability.

But the AI coding agent can then ask you follow up questions, consider angles you may not have, and generate other artifacts like documentation, data generation and migration scrip…

1000% agree.

I expect less time spent on boilerplate and documentation, and more time spent on iterating, experimenting, and increasing customer satisfaction. I also wouldn't accept "I don't kn…

Add LLM-powered chat to your app. Translate English into executable JSON commands using just TypeScript, Node, and OpenAI—no frameworks! Start extremely simple and get better at pr…

Exactly. This is precisely what I do.

That is funny, because I was a Java developer for many years, then Scala for a few years, and these days I mainly write Python, but the last thing I go for is creating a class. Tha…

I blog with stone tablets.