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

431–440 of 909 posts

Re: Open models by OpenAI

#431

Post by captainregex »

JKCalhoun wrote: post #418
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…

I do it because 1) I am fascinated that I can and 2) at some point the online models will be enshitified — and I can then permanently fall back on my last good local version.

love the first and am sad you’re going to be right about the second

Re: Open models by OpenAI

#432

Post by JKCalhoun »

mathiaspoint wrote: post #389
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…

It's really training not inference that drains the lakes.

Interesting. I understand that, but I don't know to what degree.

I mean the training, while expensive, is done once. The inference … besides being done by perhaps millions of clients, is done for, well, the life of the model anyway. Surely that adds up.

It's hard to know, but I assume the user taking up the burden of the inference is perhaps doing so more efficiently? I mean, when I run a local model, it is plodding along — not as quick as the online model. So, slow and therefore I assume necessarily more power efficient.

Re: Open models by OpenAI

#433

Post by dongobread »

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…

How up to date are you on current open weights models? After playing around with it for a few hours I find it to be nowhere near as good as Qwen3-30B-A3B. The world knowledge is severely lacking in particular.

Re: Open models by OpenAI

#434

Post by captainregex »

wizee wrote: post #417
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…

Privacy, both personal and for corporate data protection is a major reason. Unlimited usage, allowing offline use, supporting open source, not worrying about a good model being taken down/discontinued or changed, and the freedom to use uncensored models or model fine tunes are other benefits (though this OpenAI model is super-censored - “safe”). I don’t have much experience with local vision models, but for text ques…

I do think Devs are one of the genuine users of local into the future. No price hikes or random caps dropped in the middle of the night and in many instances I think local agentic coding is going to be faster than the cloud. It’s a great use case

Re: Open models by OpenAI

#435

Post by dongobread »

teitoklien wrote: post #408
hrpnk wrote: post #384

Earlier quoted context omitted.

I tried to generate a streamlit dashboard with MACD, RSI, MA(200). 1:0 for qwen3 here. qwen3-coder-30b 4-bit mlx took on the task w/o any hiccups with a fully working dashboard, graphs, and recent data fetched from yfinance. gpt-oss-20b mxfp4's code had a missing datatime import and when fixed delivered a dashboard without any data and with starting date of Aug 2020. Having adjusted the date, the update methods did n…

for now, i wouldnt rank any model from openai in coding benchmarks, despite all the false messaging they are giving, almost every single model openai has launched even the high end o3 expensive models are absolutely monumentally horrible at coding tasks. So this is expected. If its decent in other tasks, which i do find openai often being better than others at, then i think its a win, especially a win for the open so…

It is absolutely awful at writing and general knowledge. IMO coding is its greatest strength by far.

Re: Open models by OpenAI

#436

Post by diegocg »

pocketarc wrote: post #371
dust42 wrote: post #316

The 120B model badly hallucinates facts on the level of a 0.6B model. My go to test for checking hallucinations is 'Tell me about Mercantour park' (a national park in south eastern France). Easily half of the facts are invented. Non-existing mountain summits, brown bears (no, there are none), villages that are elsewhere, wrong advice ('dogs allowed' - no they are not).

Others have already said it, but it needs to be said again: Good god, stop treating LLMs like oracles. LLMs are not encyclopedias. Give an LLM the context you want to explore, and it will do a fantastic job of telling you all about it. Give an LLM access to web search, and it will find things for you and tell you what you want to know. Ask it "what's happening in my town this week?", and it will answer that with the…

The problem is that even when you give them context, they just hallucinate at another level. I have tried that example of asking about events in my area, they are absolutely awful at it.

Re: Open models by OpenAI

#437

Post by M4R5H4LL »

wizee wrote: post #417
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…

Privacy, both personal and for corporate data protection is a major reason. Unlimited usage, allowing offline use, supporting open source, not worrying about a good model being taken down/discontinued or changed, and the freedom to use uncensored models or model fine tunes are other benefits (though this OpenAI model is super-censored - “safe”). I don’t have much experience with local vision models, but for text ques…

+1 - I work in finance, and there's no way we're sending our data and code outside the organization. We have our own H100s.

Re: Open models by OpenAI

#438

Post by BizarroLand »

SR2Z wrote: post #362
BizarroLand wrote: post #286

Earlier quoted context omitted.

The slavery of free humans is illegal in America, so now the big issue is figuring out how to convince voters that imprisoned criminals deserve rights. Even in liberal states, the dehumanization of criminals is an endemic behavior, and we are reaching the point in our society where ironically having the leeway to discuss the humane treatment of even our worst criminals is becoming an issue that affects how we see our…

Prisoners themselves are the ones choosing to work most of the time, and generally none of them are REQUIRED to work (they are required to either take job training or work). They choose to because extra money = extra commissary snacks and having a job is preferable to being bored out of their minds all day. That's the part that's frequently not included in the discussion of this whenever it comes up. Prison jobs don'…

I have heard anecdotes that the choice of doing work is a choice between doing work and being in solitary confinement or becoming the target of the guards who do not take kindly to prisoners who don't volunteer for work assignments.

Re: Open models by OpenAI

#439

Post by bigyabai »

modeless wrote: post #289
bigyabai wrote: post #269

Earlier quoted context omitted.

With all due respect, you need to actually test out Qwen3 2507 or GLM 4.5 before making these sorts of claims. Both of them are comparable to OpenAI's largest models and even bench favorably to Deepseek and Opus: https://cdn-uploads.huggingface.co/production/uploads/62430a... It's cool to see OpenAI throw their hat in the ring, but you're smoking straight hopium if you think there's "no reason to run other open sourc…

> Both of them are comparable to OpenAI's largest models and even bench favorably to Deepseek and Opus So are/do the new OpenAI models, except they're much smaller.

According to the early benchmarks, it's looking like you're just flat-out wrong: https://blog.brokk.ai/a-first-look-at-gpt-oss-120bs-coding-a...

Re: Open models by OpenAI

#440

Post by dcreater »

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…

Why do any compute locally? Everything can just be cloud based right? Won't that work much better and scale easily?

We are not even at that extreme and you can already see the unequal reality that too much SaaS has engendered

Post reply on HN