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

901–909 of 909 posts

Re: Open models by OpenAI

#901

Post by FrustratedMonky »

9rx wrote: post #900
FrustratedMonky wrote: post #898

Earlier quoted context omitted.

>>> "It's the White House that wanted Trump to be candidate. They played Republican primary voters" The original comment did seem to imply that the 'White House' was in control, with a plan, and 'played' the Republicans. The original comment made the connection that Democrats were taking action. If I'm allowed to assume that when someone makes a comment, that sentences are related. That sentences can follow one anoth…

> The original comment made the connection that Democrats were taking action. Yes, it claims that the Democrats took action. That does not equate to blaming Democrats. You could blame the Democrats for what they supposedly did if that's what the randomly firing neurons in your brain conclude is most appropriate in light of the "facts" presented, but blame is just arbitrary thought. It doesn't mean anything and certai…

I think you are losing the thread of your own thoughts.

You also agreed with me in that interpretation.

Your reply >>> "Yes, that is what he thinks. Did you not read the comment? It is, like, uh, right there...

"

Are you sure you aren't using this circular logic to keep someone engaged, in order to have someone to talk to?

Re: Open models by OpenAI

#902

Post by EagnaIonat »

taikahessu wrote: post #763
EagnaIonat wrote: post #734

Earlier quoted context omitted.

Nice write up! One test I do is to give a common riddle but word it slightly to see if it can actually reason. For example: "Bobs dad has five daughters, Lala, Lele, Lili, Lolo and ???" The 20B model kept picking the answer of the original riddle, even after explaining extra information to it. The original riddle is: "Janes dad has five daughters, Lala, Lele, Lili, Lolo and ???"

A Daughter Named Bob, what a great name for AI documentary.

We call her Bobby Tables. https://xkcd.com/327/

Re: Open models by OpenAI

#903

Post by EagnaIonat »

clbrmbr wrote: post #736
EagnaIonat wrote: post #734

Earlier quoted context omitted.

Nice write up! One test I do is to give a common riddle but word it slightly to see if it can actually reason. For example: "Bobs dad has five daughters, Lala, Lele, Lili, Lolo and ???" The 20B model kept picking the answer of the original riddle, even after explaining extra information to it. The original riddle is: "Janes dad has five daughters, Lala, Lele, Lili, Lolo and ???"

I don’t get it. Wouldn’t it be Lulu in both cases?

The original riddle has a girls name. It's a common riddle so the LLM would recognize the pattern of the riddle and assumes the name is the answer.

But if it's good at reasoning it should understand that if the name is a Boys name then it is not the 5th daughter.

Now the last daughter can be called anything, but because there is a vowel pattern it should pick Lulu to solve the puzzle, but that is the wrong answer in the original puzzle.

Re: Open models by OpenAI

#904

Post by adastra22 »

FrustratedMonky wrote: post #796
username332211 wrote: post #777

Earlier quoted context omitted.

I'm pretty sure you are completely correct on the last part. Nobody in Republican management wanted a second Trump term. If the candidate wasn't Trump, Republicans would have had a guaranteed victory. Imagine that infamous debate, but with some 50-year-old youngster facing Joe Biden. It's the White House that wanted Trump to be candidate. They played Republican primary voters like a fiddle by launching a barrage of t…

You think the Democratic White House, manipulated Republicans into Voting for Trump. So it is the Democrats fault we have Trump??? Next Level Cope.

Yes? This was pretty clear at the time—-they thought Trump would be easier to run against than Haley.

Re: Open models by OpenAI

#905

Post by adastra22 »

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…

Same as the internet: porn.

Re: Open models by OpenAI

#908

Post by latexr »

latexr wrote: post #895
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 tried their live demo. It suggests three prompts, one of them being “How many R’s are in strawberry?” So I clicked that, and it answered there are three! I tried it thrice with the same result. It suggested the prompt. It’s infamous because models often get it wrong, they know it, and still they confidently suggested it and got it wrong.

Obviously I made a typo above. “Three” is the right answer, I meant that it answered there are “two” (the wrong answer).

https://i.imgur.com/DgAvbee.png

Re: Open models by OpenAI

#909

Post by keheliya »

tyho wrote: post #131
x187463 wrote: post #23

Running a model comparable to o3 on a 24GB Mac Mini is absolutely wild. Seems like yesterday the idea of running frontier (at the time) models locally or on a mobile device was 5+ years out. At this rate, we'll be running such models in the next phone cycle.

What's the easiest way to get these local models browsing the web right now?

Using LM-Studio as the frontend and Playwright-powered MCP tools for browser access. I've had success with one such MCP: https://github.com/instavm/coderunner It has a tool called navigate_and_get_all_visible_text, for example.

Here's a demo of this functionality: https://www.youtube.com/watch?v=9mLrGcuDifo

Post reply on HN