Hacker Newsnew | past | comments | ask | show | jobs | submit | mring33621's commentslogin

Congratulations?

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.

L O C A L M O D E L S

All data stays on computers that you control.

Same API. Localhost.


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.

> Try Mistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC_Q4_k_m.gguf.

Thiss sounds like such a shitpost I initially thought you were joking... but this seems to be a real model???


There's a method to the madness:

- Mistral-Nemo: the actual model developed by Mistral and Nvidia.

- 2407: likely the release date of the base model, July of 2024.

- 12B: the model has 12 billion parameters.

- Thinking: the model operates in thinking mode (generates output plan and injests it before producing actual output).

- Claude-Gemini-GPT5.2: I think this means the model was finetuned with session data from Claude, Gemini, and GTP5.2 to replicate their behavior.

- Uncensored-HERITIC: the model was uncensored using the automated Heretic method.

- Q4_k_m: the model is quantized (lossy compression) to ~5 bpw from orignal 16 bpw.


Yea, I know what the parts individually mean. I just meant as a whole it just seemed so obsurd.

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(?).


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

I have used Gemini, I have a personal subscription to ChatGPT and a corporate $5000/month allowance to Claude.

How is it better than either? How is it doing as a revenue making product?


I don't like the name. Makes it sound two faced.

Yes, I get it's a marrying of DeepMind and Google Brain teams or whatever. Still think it sounds duplicitous.


Eh, depends on what aspect of it. It's a very bad harness and is comically bad at tool calling, but as a Siri alternative and Youtube summarizer it's pretty good.

As a chatbot it's unusable due to its broken web interface.


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.

Consider applying for YC's Summer 2026 batch! Applications are open till May 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: