Hacker News: gfosco

New comment by gfosco in "Where did all the public bathrooms go?"

gfosco — Tue, 25 Aug 2026 03:41:48 +0000

They are Japanese.

New comment by gfosco in "The SpaceX Sham"

gfosco — Tue, 11 Aug 2026 18:14:11 +0000

SpaceX and Elon are the litmus test for the future. You're either with him, or your opinions are ignorant and irrelevant.

New comment by gfosco in "Our position on open-weights models"

gfosco — Tue, 28 Jul 2026 03:14:50 +0000

I have tested this exact scenario, and it works. Opus 5 had access to IDA over MCP, and I simply asked it HOW certain things were done in the target binary. Purely informational, educational, discovery, it was very helpful creating context documents. Then I took those over to GLM-5.2 to actually accomplish something.

New comment by gfosco in "Fredis: A simple in-memory Redis compatible server in Rust"

gfosco — Fri, 01 May 2026 18:11:51 +0000

I didn't feel like installing a whole redis-server service on my Windows machine, so instead I built a lightweight yet very capable clone. Maybe you'll find it handy for local development.

Fredis: A simple in-memory Redis compatible server in Rust

gfosco — Fri, 01 May 2026 18:11:51 +0000

Article URL: https://gitlab.com/foscogab/fredis

Comments URL: https://news.ycombinator.com/item?id=47978044

Points: 1

# Comments: 1

New comment by gfosco in "Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model"

gfosco — Thu, 23 Apr 2026 01:25:11 +0000

I set this up today on my 5090 at Q6_K quantization and Q4_0 KV, got 50 tokens/s consistently at 123k context, using ~28/32gb vram through LM Studio.

New comment by gfosco in "Cybersecurity looks like proof of work now"

gfosco — Thu, 16 Apr 2026 01:32:09 +0000

Yeah, it's token intensive but worth it. I built a very dumb example harness which used IDA via MCP and analyzed/renamed/commented all ~67k functions in a binary, using Claude Haiku for about $150. A local model could've accomplished it for much less/free. The knowledge base it outputs and the marked up IDA db are super valuable.

New comment by gfosco in "The Claude Code Leak"

gfosco — Thu, 02 Apr 2026 04:34:52 +0000

No you fell for someone elses joke.

New comment by gfosco in "DOGE 'Audits': A Mask for Corruption, Not Efficiency"

gfosco — Fri, 14 Feb 2025 19:04:38 +0000

Somehow not surprising to see this take on the front page. How embarrassing.

New comment by gfosco in "Rediscovering Turbo Pascal"

gfosco — Sun, 01 Sep 2024 14:23:57 +0000

I remember being an early teenager on IRC and joining a small BBS development team. I said I knew Pascal, but that was a fib... I did learn it quickly, though, and used it for many years. I can still find the code online, and see my contribution which I get a kick out of... It was a tool that you entered colored ascii frames for an animated "press any key to continue" prompt, and it output a valid pascal function file for that animation.

New comment by gfosco in "Apple M5 Chip's Dual-Use Design Will Power Future Macs and AI Servers"

gfosco — Sun, 07 Jul 2024 20:49:28 +0000

Same here... It's still amazing, and I have no legitimate reason to upgrade. Could be looked at as a failure of some sort, that they haven't given us a good reason.

New comment by gfosco in "US intelligence community is embracing generative AI"

gfosco — Sun, 07 Jul 2024 17:50:13 +0000

Not mentioned in the article, but one major provider for this is AskSage.ai, which has built up a lot of features around creating government documents, proposals, RFPs, etc.

New comment by gfosco in "The sun's magnetic field is about to flip"

gfosco — Sat, 15 Jun 2024 16:31:29 +0000

Depends who you ask. To me, NDT is unbearable too...

New comment by gfosco in "Can language models serve as text-based world simulators?"

gfosco — Sat, 15 Jun 2024 16:29:50 +0000

Not by themselves... but with a good program built around it, managing the actual state, and very careful prompting, yes. I've been thinking about this for a while, always have the desire to make a game.

New comment by gfosco in "How Meta trains large language models at scale"

gfosco — Thu, 13 Jun 2024 03:11:57 +0000

Looking to get rid of a few?....

New comment by gfosco in "Apple Intelligence for iPhone, iPad, and Mac"

gfosco — Mon, 10 Jun 2024 19:03:22 +0000

The OpenAI reference came at the end, and it appears it's mostly a fallback... an option, that users must explicitly allow every time. Hardly a dependency. Most of the time, it will be on-device or apple-hosted in "private compute cloud", not connected to OpenAI at all.

New comment by gfosco in "Vision Pro: What we got wrong at Oculus that Apple got right"

gfosco — Sun, 17 Mar 2024 04:05:35 +0000

At the end of the article, that's my takeaway too. I can't imagine going to this level of effort on the Vision Pro and not keeping it to see how the software develops.

New comment by gfosco in "Inflection-2.5: meet the best personal AI"

gfosco — Fri, 08 Mar 2024 02:20:12 +0000

It is extremely silly to think using Gab AI says anything about you, except you want good AI that isn't ruined. Extremely silly.

New comment by gfosco in "Inflection-2.5: meet the best personal AI"

gfosco — Fri, 08 Mar 2024 02:06:03 +0000

You really don't have to talk to Hitler, there are 200+ other characters to choose from... and no, I don't think there is a middle ground when it comes to censorship. Either all legal speech is okay, or it isn't. If some legal speech is so problematic, maybe it shouldn't be legal? Until then, yeah, we're going to make the necessary point.

New comment by gfosco in "Inflection-2.5: meet the best personal AI"

gfosco — Fri, 08 Mar 2024 00:50:22 +0000

If you want uncensored.. https://gab.ai is also comparing well with gpt4.