A major tech change to probably the most important email service in the world that a likely majority of people here use?

Why wouldn't it?

I hope this is satire.

Gemini 2.5 Pro is still my go to LLM of choice. Haven't used any OpenAI product since it released, and I don't see any reason why I should now.

No matter how I tried, Google AI did not want to help me write appeal brief response to ex-wife lunatic 7-point argument that 3 appellant lawyers quoted between $18,000 and $35,000. The last 3 decades of Google's scars and bruises of never-ending lawsuits and consequences of paying out billions in fines and fees, felt like reasonable hesitation on Google part, comparing to new-kid-on-the-block ChatGPT who did not hesitate and did pretty decent job (ex lost her appeal).

AI not writing legal briefs for you is a feature, not a bug. There's been so many disaster instances of lawyers using ChatGPT to write briefs which it then hallucinates case law or precedent for that I can only imagine Google wants to sidestep that entirely.

Anyway I found your response itself a bit incomprehensible so I asked Gemini to rewrite it:

"Google AI refused to help write an appeal brief response to my ex-wife's 7-point argument, likely due to its legal-risk aversion (billions in past fines). Newcomer ChatGPT provided a decent response instead, which led to the ex losing her appeal (saving $18k–$35k in lawyer fees)."

Not bad, actually.

I haven't mentioned anything about hallucinations. ChatGPT was solid on writing underlying logic, but to find caselaw I used Vincent AI (offers 2 weeks free, then $350 per month - still cheaper than cheapest appellant lawyer and I was managed to fit my response in 10 days).

That's fine, so Google sidestep it and ChatGPT did not. What point are you trying to make?

Sure I skip AI entirely, when can we meet so you hand me $35,000 check for attorney fees.

What? AI assistants are prohibited from providing legal and/or medical advice. They're not lawyers (nor doctors).

Being a layer or a doctor means being a human being. ChatGPT is neither. Also unsure how you would envision penalties - do you think Altman should be jailed because GPT gave me a link to Nexus ?

I did not find any rules or procedures with 4 DCA forbidding usage of AI.

I would use it exclusively if Google released a native Mac app.

I spend 75% of my time in Codex CLI and 25% in the Mac ChatGPT app. The latter is important enough for me to not ditch GPT and I'm honestly very pleased with Codex.

My API usage for software I build is about 90% Gemini though. Again their API is lacking compared to OpenAI's (productization, etc.) but the model wins hands down.

I've installed it as a PWA on mac and it pretty much solves it for me

For some reason, Gemini 2.5 Pro seems to struggle a little with the French language. For example, it always uses title case even when it's wrong; yet ChatGPT, Claude, and Grok never make this mistake.

Could you elaborate on your exp? I have been using gemini as well and its been pretty good for me too.

Not GP, but I imagine because going back and fourth to compare them is a waste of time if Gemini works well enough and ChatGPT keeps going through an identity crisis.

I was you except when I seriously tried gpt-5-high it turned out it is really, really damn good, if slow, sometimes unbearably so. It's a different model of work; gemini 2.5 needs more interactivity, whereas you can leave gpt-5 alone for a long time without even queueing a 'continue'.

Oh really? I'm more of a Claude fan. What makes you choose Gemini over Claude?

I use Gemini, Claude and ChatGPT daily still.

This seems promising! Great work! Any chance there will be a Ollama Modelfile for the masses?

GGUF files are available on HF: https://huggingface.co/peakji/steiner-32b-preview-gguf

I haven't personally used Ollama Modelfile, but I think it should be relatively easy to convert from GGUF?

You can now run any huggingface model using the following command

ollama run hf.co/{username}/{repository}

Example: ollama run hf.co/peakji/steiner-32b-preview-gguf:Q4_K_M

Source: https://huggingface.co/docs/hub/en/ollama

It's best to check the LMSYS chatbot arena leaderboard to find the model that best suits your needs: https://lmarena.ai/

If your into the tiling window manager experience, I would highly recommend looking into yabai + skhd + Sketchybar

- https://github.com/koekeishiya/yabai - https://github.com/koekeishiya/skhd - https://github.com/FelixKratz/SketchyBar

Some honorable mentions: Hammerspoon - Unlock insane levels of configuration/automation (https://github.com/Hammerspoon/hammerspoon) Raycast - Spotlight search replacement (https://www.raycast.com/) LuLu Firewall - An amazing FOSS firewall (https://github.com/objective-see/LuLu)

I use Amethyst https://github.com/ianyh/Amethyst in my day to day. Slightly different management philosophy but one that works well for me.

yabal requires quite some privileges. Did you check out https://github.com/nikitabobko/AeroSpace ?

FYI AeroSpace is nice but can't handle apps with tabs, like Finder. This is a non-starter issue for me at least.

Elevated privileges for yabai are optional, it works just fine without disabling SIP.

I honestly had to do a double take when I saw this make the front page. Never thought I'd see Amon Tobin top HN!

I'd recommended using llama.cpp and The Bloke's GGUF version of this model!

https://github.com/ggerganov/llama.cpp/ https://huggingface.co/TheBloke/MonadGPT-GGUF