Hacker News: jxmesth

New comment by jxmesth in "Project Glasswing: An Initial Update"

jxmesth — Sat, 23 May 2026 02:29:37 +0000

Does anyone know how we can get access to this? We're a financial institution, pretty well known locally but not internationally. Can we request access directly or maybe via bedrock/azure?

New comment by jxmesth in "Zerostack – A Unix-inspired coding agent written in pure Rust"

jxmesth — Tue, 19 May 2026 11:36:36 +0000

I'd love to test this out when it's ready : )

New comment by jxmesth in "The last six months in LLMs in five minutes"

jxmesth — Tue, 19 May 2026 05:26:21 +0000

I'm a security person and would love to hear other people's input here as I don't have that much experience with this

New comment by jxmesth in "Securing a DoD contractor: Finding a multi-tenant authorization vulnerability"

jxmesth — Tue, 05 May 2026 08:22:08 +0000

We've been thinking about testing this stuff out as well. Have you had a chance to look into stuff like XBOW/Horizon3?

New comment by jxmesth in "Zed 1.0"

jxmesth — Wed, 29 Apr 2026 18:01:04 +0000

So then the question is, why haven't they?

New comment by jxmesth in "Zed 1.0"

jxmesth — Wed, 29 Apr 2026 17:26:52 +0000

Why do I get a warning when trying to run this on Windows 11?

New comment by jxmesth in "Claude Opus 4.7"

jxmesth — Mon, 27 Apr 2026 06:11:33 +0000

Ngl I'd really love to know what you're using now instead of Claude. Desperately want to use something better

New comment by jxmesth in "Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving"

jxmesth — Tue, 21 Apr 2026 05:27:10 +0000

Yeah, it's just way easier to do via the web/mobile app but I'll give using it via the CLI a try. Thanks :)

New comment by jxmesth in "ChatGPT for Excel"

jxmesth — Mon, 20 Apr 2026 18:35:07 +0000

Thanks!

New comment by jxmesth in "Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving"

jxmesth — Mon, 20 Apr 2026 18:31:55 +0000

I gave it a try a few weeks ago tbh, I'll give it another shot tho. I mainly use their Web chats since that's easier to use and previously, qwen, deepseek, kimi, all were unable to output proper docx files or use skills.

New comment by jxmesth in "Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving"

jxmesth — Mon, 20 Apr 2026 18:30:20 +0000

Sorry for the confusion, I was actually talking about their Web based chat. Since most of my work is governance and docs, I just use their Web chats and they just refuse to output proper documents like Claude or Chatgpt do.

New comment by jxmesth in "Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving"

jxmesth — Mon, 20 Apr 2026 18:09:39 +0000

The only reason I'm stuck with Claude and Chatgpt is because of their tool calling. They do have some pretty useful features like skills etc. I've tried using qwen and deepseek but they can't even output documents. How are you guys handling documents and excels with these tools? I'd love to switch tbh.

New comment by jxmesth in "ChatGPT for Excel"

jxmesth — Thu, 16 Apr 2026 09:07:13 +0000

I tried looking this up but wasn't able to find info on this on Microsoft's website. Do you have a link for this?

New comment by jxmesth in "Pro Max 5x quota exhausted in 1.5 hours despite moderate usage"

jxmesth — Mon, 13 Apr 2026 08:43:56 +0000

I'm curious if people are going to be switching to something else. OpenAI perhaps?

New comment by jxmesth in "Claude API Error: 529"

jxmesth — Fri, 27 Mar 2026 17:49:37 +0000

Forget downtime, even when I'm able to use it, the limits make it unusable.

As an example, on my free account, I literally sent 1 message asking for information from an ongoing chat, no research, just a simple question and it exhausted it's 5 hour limit. I was using sonnet 4.6 btw. This is crazy.

Anyone else having the same issue? And if someone from Anthropic is reading this, please communicate. This feels like a bug.

New comment by jxmesth in "Show HN: I took back Video.js after 16 years and we rewrote it to be 88% smaller"

jxmesth — Wed, 25 Mar 2026 07:40:45 +0000

Any idea what the website's built with? I really like the design/UI tbh

New comment by jxmesth in "OpenAI is walking away from expanding its Stargate data center with Oracle"

jxmesth — Tue, 10 Mar 2026 10:43:43 +0000

I love how you explained this

New comment by jxmesth in "Claude Sonnet 4.6"

jxmesth — Wed, 18 Feb 2026 07:36:52 +0000

I'm curious why and how models like these give one answer for one person and a completely different answer for someone else. One reason can be memory maybe? Past conversations that tell the model "Think this way for this user"

New comment by jxmesth in "Claude Sonnet 4.6"

jxmesth — Wed, 18 Feb 2026 05:52:22 +0000

I'm curious how this would compare with codex 5.3. I've heard Codex actually is pretty good but Opus 4.6 has become synonymous with AI coding because all the big names praise it. I haven't compared them against each other though so can't really draw a conclusion.

New comment by jxmesth in "GPT-5.2 and GPT-5.2-Codex are now 40% faster"

jxmesth — Wed, 04 Feb 2026 05:40:41 +0000

Someone should create a daily benchmark site for Codex like they did for Claude