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

GPT-6 Astra

openai.com

Post reply on HN
Print view View original

711–720 of 1001 posts

Re: GPT-6 Astra

#711

Post by intenex »

Yizahi wrote: post #510
intenex wrote: post #248

The ARC-AGI-3 scorecard is extremely misleading given that it clearly states itself that "with [the responses API] harness, we estimate Sol would score in the ballpark of ~30%." but it shows a score of 7.8% for GPT-5.6 Sol presumably since if they updated the percentage for GPT-5.6 Sol to the score it would receive with the responses API harness they used for GPT-6 Astra they'd have to do the same for the percentage…

> I'd be curious to hear takes on what would make you think Astra is yet to be AGI, and what would still need to be achieved for this to effectively be AGI from this point forward. Can Astra, or any other model explain how exactly it reached this or that output result? Start with a simple query of asking to add 55+66 for example. (no LLM program can do that) Can Astra, or any other model refuse to answer or go on "th…

I'm confused what you mean by the query of adding 55 + 66. I asked 5.6 Sol on Medium (but pretty sure any model would work at any level) this query:

"Can you add 55 to 66 and explain how you reached that output result"

And received this answer:

"55 + 66 = 121.

Add the tens: 50 + 60 = 110. Add the ones: 5 + 6 = 11. Combine them: 110 + 11 = 121."

Do you mean something else? Do humans do something better than this?

Re: GPT-6 Astra

#712

Post by Forgeties79 »

mvkel wrote: post #263
intenex wrote: post #248

The ARC-AGI-3 scorecard is extremely misleading given that it clearly states itself that "with [the responses API] harness, we estimate Sol would score in the ballpark of ~30%." but it shows a score of 7.8% for GPT-5.6 Sol presumably since if they updated the percentage for GPT-5.6 Sol to the score it would receive with the responses API harness they used for GPT-6 Astra they'd have to do the same for the percentage…

Take it from the mouth of the creator of ARC-AGI: When we released ARC 3, I got asked, "when do you think a frontier model will saturate it?", and I answered "in about a year, though it depends on how much it gets explicitly targeted" That was 6 months ago, so the progress that Astra represents happened about 2x faster than I anticipated. I think the speed of progress will surprise a lot of people, and what the new m…

We are nowhere near AGI. They all talk the same, they can’t help but try to please and affirm us, and if you engage them for too long they become incoherent. They are facsimile machines. They are xeroxing language - but not even, because we can’t even duplicate our results. Too many people mistake the black box quality for magic.

Super useful, incredible tools, but not AGI. Try and roleplay a dialogue with one, make it whatever character and scenario, and see if it can sustain a coherent conversation for more than 30min with you AIM style (aol instant messenger, if that isn’t clear). Expert mode: never correct or adjust it mid conversation.

I’m not even talking about repetition and predictability. It’s nothing like talking to a person. And in a short amount of time it literally can’t form a coherent sentence.

Re: GPT-6 Astra

#713

Post by mlmonkey »

manlymuppet wrote: post #406

I have nothing to say about the actual model, but unrelated--why do so many of these demos include people buying things autonomously? Even if I did trust an AI to get everything right, it's not like the AI can read my mind. If I was ordering food normally and without AI, I would want more control over the process--looking over the options, prices, thinking about what I really want. People don't know what they really…

I often feel like the use cases, demos, etc. that these Silicon Valley employees put out are based around their needs and how they operate.

"Oh hey! Here's a demo of an AI planning out a 1-week trip to Paris!" No one in Middle America would just hand their credit card to an AI and let it come up with such a trip!

I wish SV companies took more of the middle-class (and lower-middle-class) into consideration when coming up with such demos.

(Note: I live in SF)

Re: GPT-6 Astra

#716

Post by mNovak »

mlmonkey wrote: post #713
manlymuppet wrote: post #406

I have nothing to say about the actual model, but unrelated--why do so many of these demos include people buying things autonomously? Even if I did trust an AI to get everything right, it's not like the AI can read my mind. If I was ordering food normally and without AI, I would want more control over the process--looking over the options, prices, thinking about what I really want. People don't know what they really…

I often feel like the use cases, demos, etc. that these Silicon Valley employees put out are based around their needs and how they operate. "Oh hey! Here's a demo of an AI planning out a 1-week trip to Paris!" No one in Middle America would just hand their credit card to an AI and let it come up with such a trip! I wish SV companies took more of the middle-class (and lower-middle-class) into consideration when coming…

I mean, not auto-purchasing with the card, no. But my wife has definitely used chatGPT to plan activities on the trips we've already booked.

Re: GPT-6 Astra

#717

Post by dudeinhawaii »

XCSme wrote: post #327
tintor wrote: post #78

ARC AGI-3 saturated by Astra! https://arcprize.org/leaderboard

The no-reasoning version scores 35% while the low reasoning one scores 17%? What?

I suspect this is "no reasoning set" which might be "default: medium" or perhaps some smart routing. I don't think it's literally "no reasoning".

Re: GPT-6 Astra

#718

Post by enraged_camel »

jumploops wrote: post #495

I think the thing I'm most excited about is the increase in _user prompting_. If I give a poorly constrained/ambiguous prompt, I don't want the model one-shotting assumptions left and right. The demos of Fable/GPT-6 are impressive, but "real AGI" should act more like a collaborator than either a peon or overachiever. It's a tough balance to get right, and although this has been possible to achieve with additional pro…

>>> The demos of Fable/GPT-6 are impressive, but "real AGI" should act more like a collaborator than either a peon or overachiever.

I don't really agree. The thing that makes Fable feel like an actual collaborator is its ability to sus out your real intent when you give ambiguous instructions. It's really good at it.

I watched some reviews today and came way with the impression that Astra is not better than Sol in this regard. You still have to be very specific with your instructions. For example, you can say "why is it not committed yet?" and it will give you an explanation and say it's actually ready to be committed. But it won't commit unless you explicitly say so.

That sounds like a very tedious way of working with AI agents, but I understand some people want a high level of control.

Re: GPT-6 Astra

#719

Post by huijzer »

intenex wrote: post #248

The ARC-AGI-3 scorecard is extremely misleading given that it clearly states itself that "with [the responses API] harness, we estimate Sol would score in the ballpark of ~30%." but it shows a score of 7.8% for GPT-5.6 Sol presumably since if they updated the percentage for GPT-5.6 Sol to the score it would receive with the responses API harness they used for GPT-6 Astra they'd have to do the same for the percentage…

> I am reasonably confident that there's essentially nothing that I am better than Fable at

Most things in the real world probably. I’m not saying AI can’t do it, but currently it’s bad. Try send an image of the inside of a broken toaster and how to fix. It’s laughable. Again, not saying AI will never do it, but am saying there are definitely large holes in knowledge.

Re: GPT-6 Astra

#720

Post by xixixao »

intenex wrote: post #248

The ARC-AGI-3 scorecard is extremely misleading given that it clearly states itself that "with [the responses API] harness, we estimate Sol would score in the ballpark of ~30%." but it shows a score of 7.8% for GPT-5.6 Sol presumably since if they updated the percentage for GPT-5.6 Sol to the score it would receive with the responses API harness they used for GPT-6 Astra they'd have to do the same for the percentage…

Dumb single sample example: I asked Fable 5.1 to change from hard to soft deletion in an office map backend, and it used soft deletion for data which is synced from another system, but left hard deletion on for the mapping data itself (who sits where). For me it’s a pretty severe lack of judgement (like a red flag if I asked this in an interview).
Post reply on HN