Hacker News: gtirloni

New comment by gtirloni in "Ask HN: Why is AI use decried if it has been used without attribution?"

gtirloni — Tue, 02 Jun 2026 13:41:59 +0000

I hope these people are properly attributing their work to the IDE/editor they used as well. /s

I do spend an enormous amount of time working on projects with AI assistance. When people imply that my output is any less "worthy" because of that, it gives me pause.

The reality is that there are people using AI in areas they would have no chance of producing much quickly. I understand the sentiment against that kind of situation but one shouldn't assume that's every situation.

New comment by gtirloni in "Talk Is Cheap: The Operational Impact of LLM Use"

gtirloni — Sun, 31 May 2026 21:19:38 +0000

> This is not a limitation that can be overcome by LLMs. Their generative value is in their unreliability. If you turn temperature down to zero, you get a deterministic machine - but you also break every meaningful application I know of in production.

This is not a reasonable argument. Setting the temperature down to zero does NOT give you a deterministic machine. And I have never seen that break any application in production, quite the contrary.

New comment by gtirloni in "Talk Is Cheap: The Operational Impact of LLM Use"

gtirloni — Sun, 31 May 2026 17:00:29 +0000

People are still figuring things out, there's a lot of wasted tokens, etc.

This is like complaining a student isn't as productive as a senior engineering.

I think we as an industry haven't even graduated to junior level when it comes to figuring our how to use AI to improve things.

New comment by gtirloni in "I put a datacenter GPU in my gaming PC"

gtirloni — Sun, 31 May 2026 15:27:57 +0000

> The compute is still real. The VRAM is still real. And the memory bandwidth is where it gets genuinely surprising.

sigh

New comment by gtirloni in "The solution might be cancelling my AI subscription"

gtirloni — Sun, 31 May 2026 15:22:17 +0000

As someone constantly nerd-sniped, the difficulty is that our instincts are still being formed about what this current era of AI tools can and cannot do.

So when a blocker or an idea pops up, it's very easy to use that magic-like tool to solve it quickly and then go back to whatever it's you were doing before.

However, if you care about the quality of your output, that won't be a quick detour. It will pile up with the other "quick" tasks you were doing simultaneously and that's how you end up with 5-10 sessions working on totally unrelated projects.

AI load breaks GitHub – why not other vendors?

gtirloni — Mon, 25 May 2026 12:59:21 +0000

Article URL: https://blog.pragmaticengineer.com/the-pulse-ai-load-breaks-github/

Comments URL: https://news.ycombinator.com/item?id=48266309

Points: 3

# Comments: 0

New comment by gtirloni in "Google Flow Music"

gtirloni — Fri, 24 Apr 2026 22:48:09 +0000

This website looks so terrible that I can't tell if it's really owned by Google or a scam.

New comment by gtirloni in "Ask HN: What standards or protocols exist for AI Agent permissions"

gtirloni — Tue, 14 Apr 2026 20:08:33 +0000

Check back in 5-10 years, not joking.

Reposit: Collective Intelligence for AI Agents

gtirloni — Mon, 13 Apr 2026 15:44:47 +0000

Article URL: https://reposit.bot/

Comments URL: https://news.ycombinator.com/item?id=47753703

Points: 3

# Comments: 0

New comment by gtirloni in "Ask HN: What dev tools do you rely on that nobody talks about?"

gtirloni — Thu, 02 Apr 2026 14:31:00 +0000

I think people are missing the "hidden gems" part of the question here.

New comment by gtirloni in "Ask HN: How do you know if a tweak to your AI skill made it better?"

gtirloni — Thu, 02 Apr 2026 14:23:14 +0000

How you get deterministic output though? t=0? Pydantic AI outputs?

New comment by gtirloni in "Apple Just Lost Me"

gtirloni — Wed, 25 Mar 2026 14:53:40 +0000

People who like it aren't vocal, agreed. I think this works for every outrage wave we experience online. Something to keep in mind.

New comment by gtirloni in "Apple Just Lost Me"

gtirloni — Wed, 25 Mar 2026 14:51:22 +0000

Could you emit a virtual credit card for them that you then cancel after the verification is done?

What "unfucking" looks like though? The law is mandated in the UK. What other way of age verification would work better for them?

New comment by gtirloni in "Get Shit Done: A meta-prompting, context engineering and spec-driven dev system"

gtirloni — Wed, 18 Mar 2026 15:16:15 +0000

Yes. I sometimes had to specifically ask it to NOT add any code to the specs because that would be done at a later stage.

New comment by gtirloni in "Get Shit Done: A meta-prompting, context engineering and spec-driven dev system"

gtirloni — Wed, 18 Mar 2026 15:13:24 +0000

That's definitely not a CLI wrapper. But people are calling Claude Code (clearly a TUI) a CLI so :shrug:

GSD is a collection of skills, commands, MCPs(?), helper scripts, etc that you use inside Claude Code (and others). If anything, Claude Code is the wrapper around those things and not the other way around.

Re: helper scripts. Anyone doing extensive work in any AI-assisted platform has experienced the situation where the agent wants to update 10k files individually and it takes ages. CC is often smart enought to code a quick Python script for those changes and the GSD helper scripts help in the same way. It's just trying to save tokens. Hardly a wrapper around Claude Code.

New comment by gtirloni in "Get Shit Done: A meta-prompting, context engineering and spec-driven dev system"

gtirloni — Wed, 18 Mar 2026 15:07:14 +0000

I think this shows that the model alone isn't the complete story and that these "harnesses" (as people seem to be calling them) shape a lot of the experienced behavior of these tools.

New comment by gtirloni in "Get Shit Done: A Meta-Prompting, Context Engineering and Spec-Driven Dev System"

gtirloni — Tue, 17 Mar 2026 22:39:26 +0000

GSD and superpowers aren't CLI wrappers?

New comment by gtirloni in "Get Shit Done: A meta-prompting, context engineering and spec-driven dev system"

gtirloni — Tue, 17 Mar 2026 22:33:06 +0000

Yes, it does help in that way. Maybe I'm still struggling to let go and let AI take the wheel from beginning to end but I enjoy the exploratory part of the whole process (investigating possible solutions, trying theories, doing little spikes, etc, all with CC's assistance). When it's time to actually code, I just let it do its own thing mostly unsupervised. I do spend quite a lot of time on spec writing.

New comment by gtirloni in "Get Shit Done: A meta-prompting, context engineering and spec-driven dev system"

gtirloni — Tue, 17 Mar 2026 21:33:52 +0000

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 to work.

New comment by gtirloni in "MCP is dead; long live MCP"

gtirloni — Sat, 14 Mar 2026 23:25:19 +0000

What are you investing time in instead?