Hacker News: WiSaGaN

New comment by WiSaGaN in "The Claude Code Source Leak: fake tools, frustration regexes, undercover mode"

WiSaGaN — Wed, 01 Apr 2026 12:11:55 +0000

Yeah, this seems like a personal choice, which does work out given the current result.

New comment by WiSaGaN in "Day 1 of ARC-AGI-3"

WiSaGaN — Fri, 27 Mar 2026 06:01:50 +0000

Harness is fine. I think people here are arguing what provided here to take the test is not harness.

New comment by WiSaGaN in "Detecting and Preventing Distillation Attacks"

WiSaGaN — Mon, 23 Feb 2026 22:50:27 +0000

This violates the ToS, but I don't think it's distillation. Distillation requires knowing the logits, which current API does not provide. This is just synthetic data generation. Anthropic definitely knows the difference.

New comment by WiSaGaN in "Google restricting Google AI Pro/Ultra subscribers for using OpenClaw"

WiSaGaN — Mon, 23 Feb 2026 12:41:44 +0000

Google has gigantic power over its users. Consider that for some reason, Google banned your gmail account, which you are using for large number of logins for different essential services.

New comment by WiSaGaN in "Consistency diffusion language models: Up to 14x faster, no quality loss"

WiSaGaN — Fri, 20 Feb 2026 09:08:05 +0000

I think diffusion makes much more sense than auto-regressive (AR) specifically in code generation comparing to chatbot.

New comment by WiSaGaN in "Improving 15 LLMs at Coding in One Afternoon. Only the Harness Changed"

WiSaGaN — Fri, 13 Feb 2026 06:59:32 +0000

Great article. To me, this highlights a key question in the era of rapidly advancing machine intelligence: if we know machine intelligence is progressing, what is more valuable to build for? As humans, we still find many tools useful even when doing knowledge work. For instance, a calculator. Sure, a smart person can perform calculations in their head, but it’s much easier to teach everyone how to use a calculator, which is 100% reliable in its intended domain.

In this era, we should build these kinds of tools for problems we know are straightforward ones you can’t get smarter than, even as intelligence continues to advance. Using tools like "bash" or command-line interfaces originally designed for humans is a good initial approach, since we can essentially reuse much of what was built for human use. Later, we can optimize specifically for machines, either accounting for their different cognitive structures (e.g., the ability to memorize extremely long contexts compared to humans) or adapting to the stream-based input/output patterns of current autoregressive token generators.

Eventually, I believe machine intelligence will build their own tools based on these foundations, likely a similar kind of milestone to when humans first began using tools.

New comment by WiSaGaN in "Gemini 3 Deep Think"

WiSaGaN — Fri, 13 Feb 2026 05:06:20 +0000

Yes, agentic-wise, Claude Opus is best. Complex coding is GPT-5.x. But for smartness, I always felt Gemini 3 Pro is best.

New comment by WiSaGaN in "Prism"

WiSaGaN — Wed, 28 Jan 2026 13:13:22 +0000

OpenAI has a former NSA director on its board. [1] This connection makes the dilution of the term "PRISM" in search results a potential benefit to NSA interests.

[1]: https://openai.com/index/openai-appoints-retired-us-army-gen...

New comment by WiSaGaN in "Floating-Point Printing and Parsing Can Be Simple and Fast"

WiSaGaN — Sat, 24 Jan 2026 03:54:16 +0000

Rust's `serde_json` recently switched to use a new library for floating string conversion: https://github.com/dtolnay/zmij.

New comment by WiSaGaN in "The microstructure of wealth transfer in prediction markets"

WiSaGaN — Tue, 20 Jan 2026 11:54:46 +0000

A market maker needs a premium to provide liquidity. If all else is equal, why would they take on execution time risk? This is a universal feature of continuous-trading Central Limit Order Books (CLOBs), not something unique to prediction markets.

New comment by WiSaGaN in "Reproducing DeepSeek's MHC: When Residual Connections Explode"

WiSaGaN — Mon, 12 Jan 2026 14:54:04 +0000

I guess I am asking how we know Gemini and Claude relies on the additive residual stream. We don't know the architecture details for these closed models?

New comment by WiSaGaN in "Reproducing DeepSeek's MHC: When Residual Connections Explode"

WiSaGaN — Mon, 12 Jan 2026 14:48:08 +0000

How do you know "GPT-5, Claude, Llama, Gemini. Under the hood, they all do the same thing: x+F(x)."?

New comment by WiSaGaN in "CLI agents make self-hosting on a home server easier and fun"

WiSaGaN — Mon, 12 Jan 2026 13:07:42 +0000

I have a similar experience when I found out that claude code can use ssh to conect to remote server and diagnose any sysadmin issue there. It just feels really empowered.

New comment by WiSaGaN in "New information extracted from Snowden PDFs through metadata version analysis"

WiSaGaN — Sun, 11 Jan 2026 01:56:57 +0000

I think it's likely someone already discovered this. It's just that info is not broadcasted to people who want to comment on this thread.

New comment by WiSaGaN in "Ed25519-CLI – command-line interface for the Ed25519 signature system (2024)"

WiSaGaN — Sun, 04 Jan 2026 04:04:19 +0000

I can't find the source. Anyone can point to it?

New comment by WiSaGaN in "How uv got so fast"

WiSaGaN — Sun, 28 Dec 2025 13:06:08 +0000

This argument falls apart when you look at Rust and Cargo. uv is literally trying to be "Python's Cargo." The entire blueprint came from a flagship FOSS project.

Rust's development used a structured, community RFC process—endless planning by your definition. The result was a famously well-designed toolchain that the entire community praises. FOSS didn't hold it back; it made it good.

So no, commercial backing isn't the only way to ship something good. FOSS is more than capable to ship great software when done right.

New comment by WiSaGaN in "MiniMax M2.1: Built for Real-World Complex Tasks, Multi-Language Programming"

WiSaGaN — Fri, 26 Dec 2025 12:52:19 +0000

It is now. But the limit on $20 plan is quite low and easy to use up.

New comment by WiSaGaN in "996"

WiSaGaN — Sat, 06 Sep 2025 14:48:49 +0000

Investment banks in Hong Kong were almost exclusively western back in the days with very few ethnic Chinese in senior management.

New comment by WiSaGaN in "996"

WiSaGaN — Sat, 06 Sep 2025 14:31:08 +0000

China is not the birthplace of so called '996'. Long before tech scene in China, there are a lot of investment banks doing that in HK especially for junior analysts. Calling 996 a China thing is just orientlalism. Everything bad is Chinese, everything good is western.

New comment by WiSaGaN in "LLMs tell bad jokes because they avoid surprises"

WiSaGaN — Sun, 17 Aug 2025 08:16:32 +0000

That's true. You would think LLM will condition its surprise completion to be more probable if it's in a joke context. I guess this only gets good when model really is good. It's similar that GPT 4.5 has better humor.