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

Open models by OpenAI

openai.com

Post reply on HN
Print view View original

611–620 of 909 posts

Re: Open models by OpenAI

#611

Post by spongebobstoes »

Eisenstein wrote: post #568
spongebobstoes wrote: post #556

Earlier quoted context omitted.

what does water usage mean? is that 4bn cubic meters of water permanently out of circulation somehow? is the water corrupted with chemicals or destroyed or displaced into the atmosphere to become rain?

The water is used to sink heat and then instead of cooling it back down they evaporate it, which provides more cooling. So the answer is 'it eventually becomes rain'.

I understand. but why this is bad? is there some analysis of the beginning and end locations of the water, and how the utility differs between those locations?

Re: Open models by OpenAI

#612

Post by brookst »

nl wrote: post #600
rcruzeiro wrote: post #553

Earlier quoted context omitted.

I think you are underestimating how notable a person needs to be for their information to be baked into a model.

LLMs can learn from a single example. https://www.fast.ai/posts/2023-09-04-learning-jumps/

That doesn’t mean they learn from every single example.

Re: Open models by OpenAI

#613

Post by brookst »

wubrr wrote: post #444
captainregex wrote: post #397

Earlier quoted context omitted.

I’m still trying to understand what is the biggest group of people that uses local AI (or will)? Students who don’t want to pay but somehow have the hardware? Devs who are price conscious and want free agentic coding? Local, in my experience, can’t even pull data from an image without hallucinating (Qwen 2.5 VI in that example). Hopefully local/small models keep getting better and devices get better at running bigger…

If you're building any kind of product/service that uses AI/LLMs the answer is the same as why any company would want to run any other kind of OSS infra/service instead of relying on some closer proprietary vendor API. - Costs. - Rate limits. - Privacy. - Security. - Vendor lock-in. - Stability/backwards-compatibility. - Control. - Etc.

Except many OSS products have all of that and equal or better performance.

Re: Open models by OpenAI

#614

Post by philip1209 »

captainregex wrote: post #397
cco wrote: post #357

The lede is being missed imo. gpt-oss:20b is a top ten model (on MMLU (right behind Gemini-2.5-Pro) and I just ran it locally on my Macbook Air M3 from last year. I've been experimenting with a lot of local models, both on my laptop and on my phone (Pixel 9 Pro), and I figured we'd be here in a year or two. But no, we're here today. A basically frontier model, running for the cost of electricity (free with a rounding…

I’m still trying to understand what is the biggest group of people that uses local AI (or will)? Students who don’t want to pay but somehow have the hardware? Devs who are price conscious and want free agentic coding? Local, in my experience, can’t even pull data from an image without hallucinating (Qwen 2.5 VI in that example). Hopefully local/small models keep getting better and devices get better at running bigger…

I'm excited to do just dumb and irresponsible things with a local model, like "iterate through every single email in my 20-year-old gmail account and apply label X if Y applies" and not have a surprise bill.

I think it can make LLMs fun.

Re: Open models by OpenAI

#615

Post by georgeecollins »

captainregex wrote: post #397
cco wrote: post #357

The lede is being missed imo. gpt-oss:20b is a top ten model (on MMLU (right behind Gemini-2.5-Pro) and I just ran it locally on my Macbook Air M3 from last year. I've been experimenting with a lot of local models, both on my laptop and on my phone (Pixel 9 Pro), and I figured we'd be here in a year or two. But no, we're here today. A basically frontier model, running for the cost of electricity (free with a rounding…

I’m still trying to understand what is the biggest group of people that uses local AI (or will)? Students who don’t want to pay but somehow have the hardware? Devs who are price conscious and want free agentic coding? Local, in my experience, can’t even pull data from an image without hallucinating (Qwen 2.5 VI in that example). Hopefully local/small models keep getting better and devices get better at running bigger…

There's a bunch of great reasons in this thread, but how about the chip manufacturers that are going to need you to need a more powerful set of processors in your phone, headset, computer. You can count on those companies to subsidize some R&D and software development.

Re: Open models by OpenAI

#616

Post by ptero »

nojito wrote: post #535
canvascritic wrote: post #404

Earlier quoted context omitted.

Healthcare organizations that can't (easily) send data over the wire while remaining in compliance Organizations operating in high stakes environments Organizations with restrictive IT policies To name just a few -- well, the first two are special cases of the last one RE your hallucination concerns: the issue is overly broad ambitions. Local LLMs are not general purpose -- if what you want is local ChatGPT, you will…

Pretty much all the large players in healthcare (provider and payer) have model access (OpenAI, Gemini, Anthropic)

That access is over a limited API and usually under heavy restrictions on the healthcare org side (e. g., only use a dedicated machine, locked up software, tracked responses and so on).

Running a local model is often much easier: if you already have data on a machine and can run a model without breaching any network one could run it without any new approvals.

Re: Open models by OpenAI

#617

Post by simonw »

h4ny wrote: post #610
simonw wrote: post #338

Just posted my initial impressions, took a couple of hours to write them up because there's a lot in this release! https://simonwillison.net/2025/Aug/5/gpt-oss/ TLDR: I think OpenAI may have taken the medal for best available open weight model back from the Chinese AI labs. Will be interesting to see if independent benchmarks resolve in that direction as well. The 20B model runs on my Mac laptop using less than 15GB…

> TLDR: I think OpenAI may have taken the medal for best available open weight model back from the Chinese AI labs. That's just straight up not the case. Not sure how you can jump to that conclusion not least when you stated that you haven't tested tool calling in your post too. Many people in the community are finding it substantially lobotomized to the point that there are "safe" memes everywhere now. Maybe you nee…

If you read my full post, it ends with this:

> I’m waiting for the dust to settle and the independent benchmarks (that are more credible than my ridiculous pelicans) to roll out, but I think it’s likely that OpenAI now offer the best available open weights models.

You told me off for jumping to conclusions and in the same comment quoted me saying "I think OpenAI may have taken" - that's not a conclusion, it's tentative speculation.

Re: Open models by OpenAI

#618

Post by BoorishBears »

tarruda wrote: post #499
BoorishBears wrote: post #63

Earlier quoted context omitted.

The community can always figure out hooking it up to other modalities. Native might be better, but no native multimodal model is very competitive yet, so better to take a competitive model and latch on vision/audio

> so better to take a competitive model and latch on vision/audio Can this be done by a third party or would it have to be OpenAI?

No, anyone can do it: https://github.com/haotian-liu/LLaVA

Re: Open models by OpenAI

#619

Post by simonw »

markasoftware wrote: post #589
simonw wrote: post #338

Just posted my initial impressions, took a couple of hours to write them up because there's a lot in this release! https://simonwillison.net/2025/Aug/5/gpt-oss/ TLDR: I think OpenAI may have taken the medal for best available open weight model back from the Chinese AI labs. Will be interesting to see if independent benchmarks resolve in that direction as well. The 20B model runs on my Mac laptop using less than 15GB…

The space invaders game seems like a poor benchmark. Both models understood the prompt and generated valid, functional javascript. One just added more fancy graphics. It might just have "use fancy graphics" in its system prompt for all we know.

The way I run these prompts excludes a system prompt - I'm hitting the models directly.

Re: Open models by OpenAI

#620

Post by month13 »

rmonvfer wrote: post #495
rmonvfer wrote: post #378

Earlier quoted context omitted.

I’m also very interested to know how well these models handle tool calling as I haven’t been able to make it work after playing with them for a few hours. Looks promising tho.

update: I’ve tried to use lm-studio (like the author) and the tool request kept failing due to a mismatch in the prompt template. I guess they’ll fix it but seems sloppy from lm-studio not having tested this before release.

I was road testing tool calling in LM Studio a week ago against a few models marked with tool support, none worked, so I believe it may be a bug. Had much better luck with llama.cpp’s llama-server.
Post reply on HN