Hacker News: goranmoomin

New comment by goranmoomin in "Claude Fable 5"

goranmoomin — Tue, 09 Jun 2026 18:34:52 +0000

My experience is that the GPT-family of models are very smart and figure out bugs, edge cases a bit better, but it produces code that is much less mergable – if you review the code, it introduces a lot more useless/inappropriate heavy abstractions and wrapper functions, compared to the Claude-family models which introduces the right amount of straightforward human-style code.

I can recognize so much of the GPT/Codex generated code long after it gets merged (not by me).

Additionally, the time spent on every agent turn on GPT 5.5 is much longer compared to Claude Opus 4.8, which means iterating on the code takes a lot more patience, and there's a lot more nitpicks to pick when actually using GPT 5.5 to do software engineering.

Feels like GPT-style models are more geared on doing one-shot software vibing (and handling the vibe coded mixture) compared to Claude's focus on actual software maintenance. I got a GPT Pro sub for free and wanted to cancel my Claude subscription so much, but I still keep reaching Claude models a lot more. Frustrating.

Auth.md: have agents to register accounts without a sign-up form

goranmoomin — Tue, 09 Jun 2026 18:17:32 +0000

Article URL: https://workos.com/auth-md

Comments URL: https://news.ycombinator.com/item?id=48465194

Points: 2

# Comments: 0

Let's compile Quake like it's 1997

goranmoomin — Fri, 29 May 2026 03:07:22 +0000

Article URL: https://fabiensanglard.net/compile_like_1997/

Comments URL: https://news.ycombinator.com/item?id=48318522

Points: 226

# Comments: 79

Breaking macOS App Sandbox with Archive Utility

goranmoomin — Thu, 28 May 2026 06:05:24 +0000

Article URL: https://mysk.blog/2026/05/19/cve-2026-28910/

Comments URL: https://news.ycombinator.com/item?id=48305188

Points: 2

# Comments: 0

Don't Build a General Purpose API (4 Years Later)

goranmoomin — Thu, 21 May 2026 08:12:25 +0000

Article URL: https://max.engineer/server-informed-ui-p2

Comments URL: https://news.ycombinator.com/item?id=48219404

Points: 2

# Comments: 0

Casuarina Linux: A Glibc-Based Chimera Linux Derivative

goranmoomin — Wed, 20 May 2026 10:37:04 +0000

Article URL: https://casuarina.org/news/introducing-casuarina-linux/

Comments URL: https://news.ycombinator.com/item?id=48205635

Points: 4

# Comments: 1

Pushing Local Models in Coding Agents with Focus and Polish

goranmoomin — Sat, 09 May 2026 16:42:06 +0000

Article URL: https://lucumr.pocoo.org/2026/5/8/local-models/

Comments URL: https://news.ycombinator.com/item?id=48076268

Points: 1

# Comments: 0

Amp's GPT 5.5 Model Analysis

goranmoomin — Tue, 05 May 2026 02:35:26 +0000

Article URL: https://ampcode.com/models/gpt-5.5

Comments URL: https://news.ycombinator.com/item?id=48017472

Points: 5

# Comments: 0

New comment by goranmoomin in "US and Iran agree to provisional ceasefire"

goranmoomin — Wed, 08 Apr 2026 04:53:11 +0000

TBH as an outsider, I am just so frustrated on Trump deciding that US invading Iran large scale is a great idea. (And why even is it involving Israel for gods sake?!)

If you guys wanted to be supportive to the Iranian protests, US could instead just selectively target some of the leadership and give the protests a push (and give the whole world a hint that US is supportive of them).

After 40 years of Iran constructing a thearchy government, the Iranians finally started having a huge protest on throwing up the thearchy government and possibly talking about a new west-friendly government.

And then Trump just decides to wholesale invade Iran with Israel?

That's just giving so much more reasons for the current government to be in power and the Iranians to hate the US and more generally the western world. It took 40 years for the Iranians to realize that there's enough problems in the thearchy system and want their more secularized country back; and then Trump just destroyed the whole premise!

Does the US just really think that they will be loved by everyone when they rage in and invade any random country? Do they really think like that? I'm just frustrated so much. How can the US be so egocentric?

An Appreciation for Technical Architecture

goranmoomin — Thu, 02 Apr 2026 09:08:40 +0000

Article URL: https://interconnected.org/home/2026/03/28/architecture

Comments URL: https://news.ycombinator.com/item?id=47611874

Points: 2

# Comments: 0

Run virtualized iOS with Private Cloud Compute drivers

goranmoomin — Tue, 31 Mar 2026 05:07:09 +0000

Article URL: https://github.com/wh1te4ever/super-tart-vphone-writeup

Comments URL: https://news.ycombinator.com/item?id=47582952

Points: 10

# Comments: 0

x402: What if you never had to get an API key ever again?

goranmoomin — Mon, 23 Mar 2026 16:24:09 +0000

Article URL: https://stevekrouse.com/x402

Comments URL: https://news.ycombinator.com/item?id=47491632

Points: 3

# Comments: 1

Replacing HLS/Dash: Media over QUIC

goranmoomin — Fri, 20 Mar 2026 11:44:19 +0000

Article URL: https://moq.dev/blog/replacing-hls-dash/

Comments URL: https://news.ycombinator.com/item?id=47453255

Points: 3

# Comments: 0

Your binary is no longer safe: LLM-assisted Decompilation

goranmoomin — Mon, 09 Mar 2026 01:05:10 +0000

Article URL: https://reorchestrate.com/posts/your-binary-is-no-longer-safe-decompilation/

Comments URL: https://news.ycombinator.com/item?id=47303567

Points: 4

# Comments: 1

Agentic Engineering Patterns: Anti-Patterns

goranmoomin — Thu, 05 Mar 2026 14:08:08 +0000

Article URL: https://simonwillison.net/guides/agentic-engineering-patterns/anti-patterns/

Comments URL: https://news.ycombinator.com/item?id=47261706

Points: 4

# Comments: 1

New comment by goranmoomin in "WebMCP is available for early preview"

goranmoomin — Mon, 02 Mar 2026 04:16:22 +0000

Have to say, this feels like Web 2.0 all over again (in a good way) :)

When having APIs and machine consumable tools looked cool and all that stuff…

I can’t see why people are looking this as a bad thing — isn’t it wonderful that the AI/LLM/Agents/WhateverYouCallThem has made websites and platforms to open up and allow programatical access to their services (as a side effect)?

New comment by goranmoomin in "When does MCP make sense vs CLI?"

goranmoomin — Sun, 01 Mar 2026 19:37:48 +0000

The impact on context tokens would be more of a 'you're holding it wrong' problem, no? The GH MCP burning tokens is an issue on the GH MCP server, not the protocol itself. (I would say that since the gh CLI would be strongly represented in the training dataset, it would be more beneficial to just use the CLI in this case though.)

I do think that we should adopt Amp's MCPs-on-skills model that I've mentioned in my original comment more (hence allowing on-demand context management).

New comment by goranmoomin in "When does MCP make sense vs CLI?"

goranmoomin — Sun, 01 Mar 2026 19:34:28 +0000

> The main problem with this approach at the moment is it busts your prompt cache, because LLMs expect all tool definitions to be defined at the beginning of the context window.

TBH I'm not really sure how it works in Amp (I never actually inspected how it alters the prompts that are sent to Anthropic), but does it really matter for the LLMs to have the tool definitions at the beginning of the context window in contrast to the bottom before my next new prompt?

I mean, skills also work the same way, right? (it gets appended at the bottom, when the LLM triggers the skill) Why not MCP tooling definitions? (They're basically the same thing, no?)

New comment by goranmoomin in "When does MCP make sense vs CLI?"

goranmoomin — Sun, 01 Mar 2026 19:31:34 +0000

> model understanding of the provided tool and token waste in the model trying to understand the tool and token waste in the model doing things ass backwards and inflating the context because it can't see the vastly shorter path to the solution provided by the tool and...

> But even then, throw them a tool they don't understand that has the same capabilities as a tool they do understand and you're going to burn a bunch of tokens watching it try to figure the tool out.

What I was trying to say was that this applies to both MCPs and CLIs – obviously, if you have a certain CLI tool that's represented thoroughly through the model's training dataset (i.e. grep, gh, sed, and so on), it's definitely beneficial to use CLIs (since it means less context spending, less trial-and-error to get the expected results, and so on).

However if you have a novel thing that you want to connect to LLM-based Agents, i.e. a reverse enginnering tool, or a browser debugging protocol adapter, or your next big thing(tm), it might not really matter if you have a CLI or a MCP since LLMs are both post-trained (hence proficent) for both, and you'll have to do the trial-and-error thing anyway (since neither would represented in the training dataset).

I would say that the MCP hype is dying out so I personally won't build a new product with MCP right now, but no need to ditch MCPs for any reason, nor do I see anything inherently deficient in the MCP protocol itself. It's just another tool-calling solution.

New comment by goranmoomin in "When does MCP make sense vs CLI?"

goranmoomin — Sun, 01 Mar 2026 18:05:44 +0000

I can't believe everyone is talking about MCP vs CLI and which is superior; both are a method of tool calling, it does not matter which format the LLM uses for tool calling as long as it provides the same capabilities. CLIs might be marginably better (LLMs might have been trained on common CLIs), but MCPs have their uses (complex auth, connecting users to data sources) and in my experience if you're using any of the frontier models, it doesn't really matter which tool calling format you're using; a bespoke format also works.

The difference that should be talked about, should be how skills allow much more efficient context management. Skills are frequently connected to CLI usage, but I don't see any reason why. For example, Amp allows skills to attach MCP servers to them – the MCP server is automatically launched when the Agent loads that skill[0]. I belive that both for MCP servers and CLIs, having them in skills is the way for efficent context, and hoping that other agents also adopt this same feature.

[0]: https://ampcode.com/manual#mcp-servers-in-skills