Live data from Hacker News

LM Studio Bionic: the AI agent for open models

lmstudio.ai

131–140 of 149 posts

Re: LM Studio Bionic: the AI agent for open models

#131

Earlier quoted context omitted.

They hid it well at the bottom of the page: https://lmstudio.ai/

I still must be blind cuz the main page of lmstudio.ai only says to download LM Studio 0.4.19, which I have already The word "Bionic" is never mentioned on the homepage Any other ideas?

For Mac, I see this link on the page: https://lmstudio.ai/download/bionic/latest/darwin/arm64

Re: LM Studio Bionic: the AI agent for open models

#132

Earlier quoted context omitted.

There’s actually not a lot of good harnesses that aren’t slopped together python or JS codebases, which are actually model-agnostic and don’t do some really silly things like bloating the context, too much compaction etc. There is no way I’m running a python or JS agent which is probably vibe coded, it’s just too much risk from a security and supply chain standpoint.

The harness is a security threat because it's vibecoded but the code you're having agents write for you isn't? Lol

I think it is more on distrusting python/typescript in general. Those dynamic scripting language are too easy to poison.

Re: LM Studio Bionic: the AI agent for open models

#133

Earlier quoted context omitted.

The harness is a security threat because it's vibecoded but the code you're having agents write for you isn't? Lol

I don’t vibe code though, to the extent I actually use agents to generate code it all gets reviewed and it’s essentially exactly what I would have written myself. It’s mostly things like mechanical refactors, boilerplate generation, etc.

Don't you think that is how the majority of vibecoders see themselves?

Re: LM Studio Bionic: the AI agent for open models

#134

Earlier quoted context omitted.

The harness is a security threat because it's vibecoded but the code you're having agents write for you isn't? Lol

I think it is more on distrusting python/typescript in general. Those dynamic scripting language are too easy to poison.

What makes them any easier to poison than any other language?

Re: LM Studio Bionic: the AI agent for open models

#135

Earlier quoted context omitted.

I don’t vibe code though, to the extent I actually use agents to generate code it all gets reviewed and it’s essentially exactly what I would have written myself. It’s mostly things like mechanical refactors, boilerplate generation, etc.

Don't you think that is how the majority of vibecoders see themselves?

No? Vibecoders talk about how they don't look at the code, how an IDE is unnecessary, loops, etc.

I use ghostty despite knowing mitchellh used AI to build it, because I know he's not vibe coding it. I don't use any Anthropic software for the exact opposite reason.

Re: LM Studio Bionic: the AI agent for open models

#136
post #55

Hey everyone! Yagil the founder of LM Studio here. If you want to take Bionic for a spin with GLM 5.2 / Kimi K2.6 / Kimi Coder K2.7, email your lmstudio.ai username to hn-jul16@lmstudio.ai and I'll load your account with some credits! Try it out for coding (in a "Code" project) and document creation / manipulation (in a "Work" project). In Work projects we have automatic checkpointing for every change the agent makes…

Where can i download it? The download link in the page just gets me to the usual LMStudio download page and i dont see any Bionic to download...

Re: LM Studio Bionic: the AI agent for open models

#137
post #28
post #14

This kind of thing just makes me think Apple will get to a point where they have good enough local models and good enough harnesses for doing things, and most normal people will just use them… Does the LLM become another interface to computing?

I have thought this for a while. Computing 1.0 meant that we needed to learn the computer’s language to interact with the computer fully. Computing 2.0 is that now the computer has learned our language instead.

I’m not sure what interacting with the computer fully means, but I don’t think it’s true about most computer users. They use software which invariably speaks to the user through visual metaphors and conceptual abstractions. Nothing has changed in that regard. This is true even of most programmers using high level languages.

Nothing has changed at the level of computation either, hardware speaks the same vocabulary and of electrical signals as ever.

Could you describe the change you are observing?

Re: LM Studio Bionic: the AI agent for open models

#138
post #28

Earlier quoted context omitted.

I have thought this for a while. Computing 1.0 meant that we needed to learn the computer’s language to interact with the computer fully. Computing 2.0 is that now the computer has learned our language instead.

I’m not sure what interacting with the computer fully means, but I don’t think it’s true about most computer users. They use software which invariably speaks to the user through visual metaphors and conceptual abstractions. Nothing has changed in that regard. This is true even of most programmers using high level languages. Nothing has changed at the level of computation either, hardware speaks the same vocabulary an…

People don’t type so much anymore.

Re: LM Studio Bionic: the AI agent for open models

#139
post #89

I’m worried about the switch in business model here, which is part of the reason I just switched to LM Studio from Ollama. > use the largest frontier open source models through LM Studio Secure Cloud

To be fair, Ollama has been pushing their own cloud offering just as much. For some of the latest big models (from Minimax, GLM, Kimi, etc.) even after months they still don't provide official downloadable versions, just their cloud one.

Because none of those models run on any hardware Ollama was intended for? You ain’t going to run 1.6Tq4 model on your macbook pro with 128GB memory anyway.
Post reply on HN