Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Get Shit Done: A meta-prompting, context engineering and spec-driven dev system

github.com

Post reply on HN
Print view View original

211–220 of 278 posts

Re: Get Shit Done: A meta-prompting, context engineering and spec-driven dev system

#211

Post by sigbottle »

gtirloni wrote: post #21

I was using this and superpowers but eventually, Plan mode became enough and I prefer to steer Claude Code myself. These frameworks are great for fire-and-forget tasks, especially when there is some research involved but they burn 10x more tokens, in my experience. I was always hitting the Max plan limits for no discernable benefit in the outcomes I was getting. But this will vary a lot depending on how people prefer…

Yup yup yup. I burned literally a weeks worth of the 20$ claude subscription and then 20$ worth of API credits on gsdv2. To get like 500 LOC.

And that was AFTER literally burning a weeks worth of codex and Claude 20$ plans and 50$ API credits and getting completely bumfucked - AI was faking out tests etc.

I had better experiences just guiding the thing myself. It definitely was not a set and forget experience (6 hours of constant monitoring) but I was able to get a full research MVP that informed the next iteration with only 75% of a codex weekly plan.

Re: Get Shit Done: A meta-prompting, context engineering and spec-driven dev system

#213

Post by rsoto2 »

prakashrj wrote: post #13
rsoto2 wrote: post #3

Earlier quoted context omitted.

I could copy 250k lines from github. Faster than using ai. Cheaper. Code is better tested/more secure. I can learn/build with other humans.

This is how I test my code currently. 1. Backend unit tests — fast in-memory tests that run the full suite in ~5 seconds on every save. 2. Full end-to-end tests — automated UI tests that spin up a real cloud server, run through the entire user journey (provision → connect → manage → teardown), and verify the app behaves correctly on all supported platforms (phone, tablet, desktop). 3. Screenshot regression tests — ev…

sounds like your only measure of good tests is how quickly the llm can produce and run them. not a good metric.

LOL screenshot regression. You're still not a dev buddy read some books

Re: Get Shit Done: A meta-prompting, context engineering and spec-driven dev system

#216

Post by joshribakoff »

giancarlostoro wrote: post #209

Nice, I like the UI more than mine, I built a similar tool out of minor frustrations with some design choices in Beads, mine uses SQLite exclusively instead of git or hard files, been using it for all my personal projects, but havent gone back to try and refine what I have a little more. One thing a lot of these don't do that I added to mine is synching to and from GitHub. I want people to see exactly what my local t…

The “secret sauce”? RPI (research plan implement) is far from a secret concept. Heck, its in the official docs! Not secret.

“never forgetting”? Its still a probabilistic model.

You’re framing it like you discovered some secret techniques that eludes 100s of millions of users and overcame the architectural limits of the model.

Re: Get Shit Done: A meta-prompting, context engineering and spec-driven dev system

#217

Post by joshribakoff »

dboreham wrote: post #204
coopykins wrote: post #171

There are so many of these "meta" frameworks going around. I have yet to see one that proves in any meaningful way they improve anything. I have a hard time believing they accomplish anything other than burn tokens and poison the context window with too much information. What works best IME is keeping things simple, clear and only providing the essential information for the task at hand, and iterating in manageable s…

From my experience they are motivated by these two issues that you run into when using Claude Code (or similar tool): 1. The LLM is operating on more what you'd call "guidelines" than the rules -- it will mostly make a PR after fixing a bug, but sometimes not. It will mostly run tests after completing a fix, but sometimes not. So there's a sentiment "heck, let's write some prompt that tells it to always run tests aft…

After a while many people then realize this often produces worse results by injecting additional noise in context like the overhead of invoking the gh cli and parsing json comments or worse the mcp.

But they get the dopamine loop of keeping the loop alive, flashing colors, high score/token use, and plausible looking outputs — so its easy to deceive oneself into thinking something remarkable was discovered

Re: Get Shit Done: A meta-prompting, context engineering and spec-driven dev system

#219

Post by BTAQA »

Built my first SaaS as a frontend dev with no backend experience using a similar approach. The key shift was treating Claude Code as a senior developer who needs clear specs, not a magic box. The more precise the context and requirements, the better the output. Vague prompts produce vague code.

Re: Get Shit Done: A meta-prompting, context engineering and spec-driven dev system

#220

Post by toastal »

tkiolp4 wrote: post #54
prakashrj wrote: post #11

Earlier quoted context omitted.

A self-hosted VPN server manager: a TypeScript/Hono backend that runs on your own VPS, paired with a SwiftUI iOS/macOS app. It lets you provision cloud servers across multiple providers (Hetzner, DigitalOcean, Vultr), manage them via a Tailscale-secured connection with TLS pinning, and control an OpenClaw gateway. I will open source it soon in few weeks, as I have still complete few more features.

Please don’t.

Please do. Poison the training.
Post reply on HN