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

241–250 of 278 posts

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

#241

Post by sigbottle »

FromTheFirstIn wrote: post #224
sigbottle wrote: post #211

Earlier quoted context omitted.

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 hour…

You spent $25 on 500 LOC?

Well, there were milestones and docs and extra scaffolding that the gsd system produces, but yes. and it didn't seem like progress was going to go any faster.

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

#242

Post by soorya3 »

The only tool you need is the one that saves tokens... the one that saves tokens ... the one that saves tokens. Currently I don't know any.

Claude code itself consumes lot of tokens when not needed. I have to steer it a lot while building large applications.

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

#243

Post by petesergeant »

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…

I have my own mini framework that marries Claude and Codex. When I see the clangers that Claude by itself produces that Codex catches, I can’t see how I’d ever just let a single agent do its thing.

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

#244

Post by gavinray »

hatmanstack wrote: post #236
LogicFailsMe wrote: post #198

Earlier quoted context omitted.

I find simple Ralph loops with an implementer and a reviewer that repeat until everything passes review and unit tests is 90% of the job. I would love to do something more sophisticated but it's ironic that when I played both agents in this loop over the past few decades, the loop got faster and faster as computers got faster and faster. Now I'm back to waiting on agentic loops just like I used to wait for compilatio…

Curious what you mean by "played both agents" and "faster and faster"? API calls are API Calls or are you running an open-source model locally?

Rephrasing of the post in case it's clearer:

"I would love to do something more sophisticated, but it's ironic that when I performed both of the duties done nowadays by agents, the development loop got faster and faster as computers got faster and faster."

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

#245

Post by redmattred »

soorya3 wrote: post #242

The only tool you need is the one that saves tokens... the one that saves tokens ... the one that saves tokens. Currently I don't know any. Claude code itself consumes lot of tokens when not needed. I have to steer it a lot while building large applications.

Here's one: https://www.rtk-ai.app/ (https://github.com/rtk-ai/rtk)

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

#246

Post by ccanassa »

duskdozer wrote: post #191
sarchertech wrote: post #181

Earlier quoted context omitted.

That’s like asking why don’t we switch from reviewing PRs to reviewing jira tickets. There’s probably a world where you could do that if the spec was written in a formal language with no ambiguity and there was a rigorous system for translating from spec to code sure.

Hm, that's an interesting concept. What if we were able to create an unambiguous, rigorous specification language for creating prompts so that we could get consistent and predictable output from AI? Maybe we could call it a "prompt programming language" or something

That exists, it's called code.

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

#247

Post by alasano »

gbrindisi wrote: post #163
alasano wrote: post #60

Earlier quoted context omitted.

I also like openspec. I think these type of systems (gsd/superpowers) are way too opinionated. It's not that they can't or don't work. I just think that the best way to truly stay on top of the crazy pace of changes is to not attach yourself to super opinionated workflows like these. I'm building an orchestrator library on top of openspec for that reason.

I am doing something similar: I use openspec to create context and a sequential task list that I feed to ralph loops, so that i’m involved for the planning and the verification step but completely hands off the wheel during code generation.

Exactly that. I created an "Open Ralph" loop initially within Claude directly with review gates per phase in the OpenSpec task list.

But it was always just a workaround to what I truly wanted (what I'm building now), a full external managed orchestrator loop. The agents aren't aware of the loop, they don't need to be.

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

#248

Post by jdwyah »

I used GSD for a bit. It was helpful for a side project where I constantly forgot where I was in implementation. Helpful to be able to just say "Do the next thing"

I would imagine that for a non-engineer trying to code it would be quite useful / deliver a better result / less liable to end up in total mess. But for experienced engineers it quickly felt like overkill / claude itself just gets better and better. Particularly once we got agent swarms I left GSD and don't think I'll be back. But I would recommend it to non coders trying to code.

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

#249

Post by j45 »

jdwyah wrote: post #248

I used GSD for a bit. It was helpful for a side project where I constantly forgot where I was in implementation. Helpful to be able to just say "Do the next thing" I would imagine that for a non-engineer trying to code it would be quite useful / deliver a better result / less liable to end up in total mess. But for experienced engineers it quickly felt like overkill / claude itself just gets better and better. Partic…

In your experience do you think something like this could feed into agent swarms pretty well?

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

#250

Post by codebolt »

whalesalad wrote: post #138
Rapzid wrote: post #135

Earlier quoted context omitted.

I use GitHub Copilot and unfortunately there has been a weird regression in the bundled Plan mode. It suddenly, when they added the new plan memory, started getting both VERY verbose in the plan output and also vague in the details. It's adding a lot of step that are like "design" and "figure out" and railroads you into implementation without asking follow-up questions.

I find that even with opus 4.6, copilot feels like it’s handicapped. I’m not sure if it’s related to memory or what but if I give two tasks to opus4.6 one in CC and one in Copilot, CC is substantially better. I’ve been really enjoying Codex CLI recently though. It seems to do just as well as Opus 4.6, but using the standard GPT 5.4

Opus 4.6 has a 200k context limit in Copilot. Could be the issue.
Post reply on HN