mring33621

Kinda shitty but just a minor speed bump. Just run Windows on a VM in Linux, right?

Maybe it's because I don't know anything about how claude plugins work, but I find it odd that there's no actual TS code in the mentioned repo: https://github.com/LegalRabbit-AI/legalrabbit-docx-claude-pl...

There is a zip file of code in the releases though. I wonder if the LPGL 3.0 license covers that?

UPDATE: the zip file is just the repo itself. So everything interesting is in the legalrabbit-docx-mcp.exe, contained in the GitHub releases.

What a tease.

I have a Macbook Pro with M1 Max processor. I build llama.cpp from main every week or so, which I'm pretty sure includes Apple's 'metal' acceleration. That's it tho.

I use opencode with local Qwen 3.6 or GLM 4.7 models, running in llama.cpp, and am very happy with it for a lot of coding and code analysis work. Infinite tokens!

It's not crazy, it's visionary!

I was scolded by my manager, who finished with the cliche, "we are open to suggestions for improvements"

We got a special thing that did special things. Yay!

But they get mad when you tell them that their processes are Kafkaesque!

Ask me how I know.

Because it looks cool!

well, if it's already there and keeps coming back, can I use it?

A local Gemini Nano might be useful!

looks like Klingon

OMG it's a secret message!

Duh! Windmills are very dangerous!

sounds way low to me

AKA: "Increase other random non-income taxes and government fees"

holy shit!

Congratulations?

It is! I like to try the variations from possibly 'interesting' people.

Some of them are good. Others randomly break into gibberish and Chinese poetry(?).

The best kind of project. I'm trying this today. I've been happily using OpenCode so far.

Often you have to choose the 'least bad' choice. Mistral may be that, from an EU POV.

Try Mistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC_Q4_k_m.gguf. This 7.5GB model runs well in llama.cpp on my 2021 Macbook Pro and is good at both coding and business document analysis tasks.

L O C A L M O D E L S

All data stays on computers that you control.

Same API. Localhost.

AI SLOP ASSESSMENT:

Feature | Legacy Rules (Pre-2026) | New Rules (SR-FINRA-2025-017)

--------------------------------------------------------------------------------------------

PDT Designation | Based on 4+ trades in 5 days | Eliminated

Min. Equity | $25,000 | $2,000 (Standard Margin Min)

Buying Power | 4x Maintenance Excess | Based on real-time IML

Constraint | Trade Count | Intraday Risk/Deficit

Gemini is a great product

No. It's more fun than ever, IMHO!

Agree. I have learned so much, so rapidly, over the last 3 years, thanks to these AI tools.

These things can be a poisoned chalice, leading to weaker long-term performance, or they can be a force multiplier. It's up to you how you use them.

Dammit that was my idea!

I'd rather work for an AI than some of the managers I've had in the past.

Now do the best cup of coffee!

The moat is that they saved their money and can remain in business indefinitely!

Or not