Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ollama's new app

ollama.com

Post reply on HN
Print view View original

111–120 of 299 posts

Re: Ollama's new app

#111

Post by steve_adams_86 »

pmarreck wrote: post #102
thorum wrote: post #97

If you’re a power user of these LLMs and have coding experience, I actually recommend just whipping together your own bespoke chat UI that you can customize however you like. Grab any OpenAI compatible endpoint for inference and a frontend component framework (many of which have added standard Chat components) - the rest is almost trivial. I threw one together in a week with Gemini’s assistance and now I use it every…

[flagged]

> Tell me you're not in charge of young kids

Yeah, my wife would murder me as our kids yelled at me for various things

Re: Ollama's new app

#112

Post by halJordan »

whoisstan wrote: post #109
throwawaylaptop wrote: post #101

I must be stupid because I don't understand how this is different than having several tabs open in a browser with all the AI services I'd like open?

Ollama runs all local, away from prying corps.

OK there are plenty of webuis that consume private apis, even ollama ones

Re: Ollama's new app

#113

Post by bapak »

thorum wrote: post #97

If you’re a power user of these LLMs and have coding experience, I actually recommend just whipping together your own bespoke chat UI that you can customize however you like. Grab any OpenAI compatible endpoint for inference and a frontend component framework (many of which have added standard Chat components) - the rest is almost trivial. I threw one together in a week with Gemini’s assistance and now I use it every…

This is the most "just build your own Linux" comment I read this year.

Just download some tool and be productive within seconds, I'd say.

Re: Ollama's new app

#114

Post by halJordan »

pmarreck wrote: post #108
Eisenstein wrote: post #93

Earlier quoted context omitted.

OpenWebUI refuses to support MCP and uses an MCP to OpenAPI proxy which often doesn't work. If you don't like or need MCP, then it is a good choice.

> refuses to support MCP Why is that? Seems the way to go to add tooling to any LLM that is tool-capable

The dev is very opinionated

Re: Ollama's new app

#115

Post by ellg »

bapak wrote: post #113
thorum wrote: post #97

If you’re a power user of these LLMs and have coding experience, I actually recommend just whipping together your own bespoke chat UI that you can customize however you like. Grab any OpenAI compatible endpoint for inference and a frontend component framework (many of which have added standard Chat components) - the rest is almost trivial. I threw one together in a week with Gemini’s assistance and now I use it every…

This is the most "just build your own Linux" comment I read this year. Just download some tool and be productive within seconds, I'd say.

Kinda odd to be so dismissive of this mindset given this websites title. Whipping up your own chatui really is not that hard and is a pretty fun exercise. Knowing how your tools work and being able to tweak them to your specific usecases kinda rules!

Re: Ollama's new app

#116

Post by AnonC »

pentagrama wrote: post #44

Looks like a big pivot on target audience from developers to regular users, at least on the homepage https://ollama.com/ as a product. Before, it was all about the CLI versions of Ollama for devs, now it's not even mentioned. At the bottom of the blog post it says: > For pure CLI versions of Ollama, standalone downloads are available on Ollama’s GitHub releases page. Nothing against that, just an observation. Previou…

I’d heard of Msty and briefly tried it before. I checked the website again and it looks quite feature rich. I hadn’t known about LM Studio, and I see that it allows commercial use for free (which Matt doesn’t).

How would you compare and contrast between the two? My main use would be to use it as a tool with a chat interface rather than developing applications that talk to models.

Re: Ollama's new app

#117

Post by Arubis »

pmarreck wrote: post #102
thorum wrote: post #97

If you’re a power user of these LLMs and have coding experience, I actually recommend just whipping together your own bespoke chat UI that you can customize however you like. Grab any OpenAI compatible endpoint for inference and a frontend component framework (many of which have added standard Chat components) - the rest is almost trivial. I threw one together in a week with Gemini’s assistance and now I use it every…

[flagged]

> I don't know if parenting hits the "developer-tinkerer class" harder than others, but damn.

I sort of suspect so? Devs of parenting age trend towards being neurospicy, and dev work requires sustained attention with huge penalties for interruptions.

Re: Ollama's new app

#118

Post by jay_kyburz »

OK, for those interested, I have a Ryzen9 2700 with a 12GB RX6750XT and downloaded Gemma3:4b because that was what the app suggested first.

The speed seems fine to me, but the hallucinations are wild, completely wrong on a few things I like to test the commercial offerings on.

For simple questions about the lua language and how to do things in Unity game engine the results look fairly OK.

Re: Ollama's new app

#119

Post by kanestreet »

Eisenstein wrote: post #96
mchiang wrote: post #61

Earlier quoted context omitted.

Choice is good but here is why prefer Ollama over others (I'm biased because I work on Ollama). Supporting multiple backends is HARD. Originally, we thought we'd just add multiple backends to Ollama - MLX, ROCm, TRT-LLM, etc. It sounds really good on paper. In practice, you get into the lowest common denominator effect. What happens when you want to release Model A together with the model creator, and backend B doesn…

Sure, those are all difficult problems. Problems that single devs are dealing with every day and figuring out. Why is it so hard for Ollama? What seems to be true is that Ollama wants to be a solution that drives the narrative and wants to choose for its users rather than with them. It uses a proprietary model library, it built itself on llama.cpp and didn't upstream its changes, it converted the standard gguf model…

^^^ absolutely spot on. There’s a big element of deception going on. I could respect it (and would trust the product more) if they were upfront about their motives and said “yes we are a venture backed startup and we have profit aspirations, but here’s XYZ thing we can promise. Instead it’s all smoke and mirrors … super sus.

Re: Ollama's new app

#120

Post by jay_kyburz »

coder543 wrote: post #95

I am somewhat surprised that this app doesn't seem to offer any way to connect to a remote Ollama instance. The most powerful computer I own isn't necessarily the one I'm running the GUI on.

The app does have a function to expose Ollama to the network, so perhaps its coming?
Post reply on HN