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

LM Studio Bionic: the AI agent for open models

lmstudio.ai

Post reply on HN
Print view View original

71–80 of 149 posts

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

#71

Post by sebmellen »

opallimetea wrote: post #70
yags wrote: 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…

[flagged]

Are you using a local model or one of the hosted ones? I don't think a harness can influence the range of outcomes that much.

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

#72

Post by slopinthebag »

Geezus_42 wrote: post #60
slopinthebag wrote: post #57

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 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.

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

#75

Post by IronWolve »

It was fun to try out which local models made better agents. Few thoughts.

* locked to a single dir, so no system wide access.

* no local web search, can be fixed ddg or local mcp.

* no ssh, I want to have it ssh into my server and do the work.

* doesnt show the model being loaded, needs a bar/% counter.

* Can you drag/drop documents in the work dirs, or only + add them?

I love lm-studio, so cant wait to see how this goes. For local I normally use opencode + lmstudio.

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

#76

Post by satvikpendem »

docheinestages wrote: post #48
satvikpendem wrote: post #41

Earlier quoted context omitted.

Use Unsloth Studio, it's actually open source and I trust Unsloth via their quantized models a lot more than LM Studio.

Any VC-backed company will eventually pivot.

Use now then switch later. Such is the life of a software user.

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

#77

Post by jfaat »

SOLAR_FIELDS wrote: post #31
gehsty wrote: 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?

This question hinges on whether model advancement plateaus enough for machine sized models to compare to frontier performance. If it does, the answer is yes. If it doesn’t, the answer is no

I disagree. The point of the frontier models is to do everything as well as possible ("AGI" race or whatever) but smaller models with some RL are going to be the clear winner for a ton of use cases. Think about all the use cases for LLMs that would never be economical at frontier inference costs, and in no way need it. You don't need or even want a phd polymath helping you with small productivity tasks that most people use computers for every day. It's often overwrought and annoying. I don't even really like the frontier models for coding for this reason. They're constantly blowing up scope and you have to fight it constantly.

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

#78

Post by christoph »

woadwarrior01 wrote: post #64
freehorse wrote: post #34

Earlier quoted context omitted.

For now, it seems that direction that lm studio is taking for enterprise market is "local ai deployment support". They recently launched "lm link" which basically uses tailscale to create e2ee connections between computers running lm studio where you are logged in. Granted one can also setup tailscale or their own vpn themselves and use llama-server, but I guess it is simpler to provide it out of the box. In any case…

> In any case I am not sure pivoting from running local models to "cloud offering" (as in providing llm inference at their severs) is a sensible choice granted there is already competition in that space and they have no leverage there. I agree. Incidentally, this is exactly what ollama are doing too.

I can definitely see a world where you run stuff local first, for all the reasons we know. Sometimes, you are going to want more powerful models, faster, you’re travelling, etc. You might only use these 5 to 10% of the time, but I’m guessing that’s the market they want.

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

#79

Post by Aerialoo »

dofm wrote: post #45
thehamkercat wrote: post #6

A friendly reminder that both LM Studio app and now this new LM Studio Bionic app are closed source. Since most people are unaware of this fact.

I am aware of it, and I dabble with Unsloth Studio and use the llama-server approach. I would obviously prefer an open source, open weights stack. But I guess a paradox is that as long as there are open source options I could use, a solid agentic environment that I can use with my own open weights is something I might pay for, in a similar sort of way to paying for a Mac when I could use only Linux. If someone wanted…

I seriously don't understand the apple glazing. They are pretty much completely out of the picture and are one of the most anti consumer anti open-source companies. Yet developers STILL hope for Apple acquisitions and being saved... Or something like that... We have llama.cpp, vLLM, opencode, hermes and countless other mature great open source tools that don't require a anti-consumer company's hands in the jar.

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

#80

Post by lrae »

yags wrote: 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…

Wouldn't mind taking a look :)
Post reply on HN