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

OpenAI begins rolling out GPT-6 Astra

cnbc.com

Post reply on HN
Print view View original

261–270 of 277 posts

Re: OpenAI begins rolling out GPT-6 Astra

#261

Post by bredren »

dist-epoch wrote: post #235
zzleeper wrote: post #14

(Posting partly so I can revisit my predictions when they open access more widely) A big problem I have with OpenAI's models (and of course Claude) is that they tend to write the most over-engineered pieces of code, beyond the imagination of any architecture's astronaut. Just this week I asked 5.6-sol-ultra to update a 1000 LOC python script I had, to "incorporate the key lessons learned when using it for another pro…

The defaults are bad, but these models are highly steerable. For simple scripts adding to the prompt something like "do not over engineer, do not gold plate, no CLI args, keep it simple" does wonders. For whole projects, I have a 3 page anti-bloat.md which describes what not to do, stuff like: > Minimize lines of code, number of files, classes, protocols, factories, wrappers, and dependency-injection objects. Prefer…

I also use "do not overengineer and do not gold plate." I also sometimes tell it to "avoid bike shedding." These are high signal words to the model(s) and they work!

I also have found what I believe is a bad training bias in the design of release related CI workflows toward proof of release artifact provenance.

Both major frontier models love provenance programming in CI, so much that they will spin endlessly trying to solve basic CI functionality at the same time as ensuring SHA's match up across lengthy (often already complex) cross-system pipelines.

I had thought some of my durable context was causing this, and sought to strip anything that might be triggering this behavior.

But then I come upon some more work in release workflows comes up, and boom its back! I couldn't believe it, I called the AI out on it and it agreed it had been told specifically not to do this but was doing it anyway. It did kindly stop and remove the commit(s).

Somewhere, something was oversampled in training because the AI will try their damndest to build this stuff. The worst of it is that it can often involve lengthy, sometimes resource-heavy CI runs so the validation of this unnecessary stuff can have very long feedback loops.

And, sometimes you actually need the provenance. In this case, I've had success forcing the AI to split the work up into functional capability completely devoid of artifact ~chain of custody and get that right before attempting any kind of provenance work.

Bit of a rabbit hole on this, but the above cost me a lot of burned tokens so hopefully helps someone...or some AI.

Re: OpenAI begins rolling out GPT-6 Astra

#262

Post by WelkinFolk »

vonneumannstan wrote: post #186
roarcher wrote: post #138

Earlier quoted context omitted.

Even if all that is true, why shouldn't people be able to joke about it? Your sentiment is borderline AI worship.

I don't think they were joking.

Sarcastic quips are basically the most human response to any new situation. Let us have fun

Re: OpenAI begins rolling out GPT-6 Astra

#263

Post by Davidzheng »

HarHarVeryFunny wrote: post #234
famouswaffles wrote: post #231

Earlier quoted context omitted.

All intelligence is jagged. Human intelligence is jagged, so is Cetacean intelligence, so is Ape intelligence, so is Corvid intelligence. You could re-orient that statement for any species of intelligence relative to the other, or even individuals within a species. The big problem here is people being so convinced of their specialness they'll just keep sticking their heads in the sand, until we essentialy create God,…

I'm not sure it's accurate to call human intelligence jagged - it seems (perhaps largely thanks to language) that we're able to make progress on anything we set our minds to, and of course we're now in process of building AI that will eventually be able to do things that we ourselves couldn't, whether due to computational demands, or memory capacity, or having sensory inputs that we don't have, etc. But at the end of…

I'm not sure it's meaningful to compare across different types of intelligence--but I don't think human intelligence is so special that we can pretend it's much less jagged than all other animals for sure. Our scales of models are also not far off biological, probably less efficient but not like astronomically so i would guess.

But anyhow I agree that inference-time learning doesn't exist and it's a big issue still I think.

Re: OpenAI begins rolling out GPT-6 Astra

#264

Post by dgellow »

vonneumannstan wrote: post #236
dgellow wrote: post #220

Earlier quoted context omitted.

I’m on HN almost every day advocating for a complete ban of the technology because of its risks and externalities…

Then why are we arguing? I agree with you, I'm highlighting the fact that people making light of the technology is dangerous

I’m not the one arguing, I asked you if your comment was satire. I agree with the sibling comment, it reads like AI religious worshipping

Re: OpenAI begins rolling out GPT-6 Astra

#265

Post by asaddhamani »

So not a single normal human being can access the model yet, just some super limited handful of organizations, but they’ve announced the model as though it’s available to everyone already.

I guess that’s the world we live in now, Anthropic did similar with Mythos and even Fable if I recall correctly.

Re: OpenAI begins rolling out GPT-6 Astra

#266

Post by xp84 »

PepegaRoach wrote: post #245
bethekidyouwant wrote: post #244

Earlier quoted context omitted.

Why would you put it on ultra high thinking and let it run all night to do a simple task it makes no sense the error is the users. And of course OpenAI is gonna let you burn as many tokens as you want doing this.

On the flip side if its a super simple task, surely a "next gen dev replacing" LLM can figure out when to stop. Even more when it's a higher level of reasoning.

I think this is fair. If you ask a staff engineer to delete the duplicate files from a directory, he will likely do it faster and more efficiently than a level 2 engineer.

But perhaps this is the kind of thing that the best 'ai guys' out there solve with something as surprisingly simple as an instruction to "Always try a simple solution first and optimize only if you find clear proof of a problem." I feel like prompts like that seem too simple to work, but some of the time they shockingly do.

Re: OpenAI begins rolling out GPT-6 Astra

#267

Post by jaggederest »

HarHarVeryFunny wrote: post #260
jaggederest wrote: post #259

Earlier quoted context omitted.

> If a system can truly learn for itself then it shouldn't need to be pre-trained with language, but rather should be able to learn by immersion and practice the same way we do, and the same way a dog learns to follow commands. You can't do this by leaving notes to yourself - the learning mechanism needs to be animal-like and update the systems weights in response to prediction failure - a runtime version of the way…

You can't take notes before you've learned language, so if that's how you propose to learn then you are doomed to build something with less learning capability than an human brain. Maybe you don't care - if you just want to push to see how far an LLM can go that's fine. but it's not going to be superhuman-level, or even human-level, if it doesn't have the learning ability of a human. If it relies on language and note…

Okay, nowhere did I say it would be before they learned language. I said we could use models that can trivially build notetaking systems to auto-improve themselves by taking, refining, and updating notes as a memory system to exceed the x token context threshold.

> but it's not going to be superhuman-level, or even human-level, if it doesn't have the learning ability of a human. If it relies on language and notes to itself then it is just an LLM.

Why do you think that? You do a lot of assuming a thing to be true without any clear reasoning or evidence. I'm talking about a system, including a LLM, that acts in a way that is equivalent to or better than an average human at a large range of tasks, such that is generally capable of learning and problem solving similar to the degree of success humans have. All these specific criteria about what is "actually human" is not the point. We know how to make more humans, I'm talking about a form of intelligence that we are creating that is genuinely alien, so holding to "well it doesn't work the same as a human" is an impossible bar. If you reverse the situation, humans are by no means LLM-equivalent intelligences - perfect memory of long form content, rapid calculation, instantaneous tool calling - a hypothetical silicon based lifeform would dismiss us as "really not intelligent at all, they can't even do multiple floating point calculations per second in their head", and I think that would be similarly silly.

Re: OpenAI begins rolling out GPT-6 Astra

#268

Post by krzyk »

MallocVoidstar wrote: post #126
jrflo wrote: post #62

Earlier quoted context omitted.

So if you use the non-promotional price for sol it's only 25% higher?

Sol's normal pricing is $5/$30.

Yeah, but I assume in November (when current promo $4/$20) ends, we will have GPT-6 Sol/Terra/Luna.

Re: OpenAI begins rolling out GPT-6 Astra

#269

Post by Planktonne »

dist-epoch wrote: post #235
zzleeper wrote: post #14

(Posting partly so I can revisit my predictions when they open access more widely) A big problem I have with OpenAI's models (and of course Claude) is that they tend to write the most over-engineered pieces of code, beyond the imagination of any architecture's astronaut. Just this week I asked 5.6-sol-ultra to update a 1000 LOC python script I had, to "incorporate the key lessons learned when using it for another pro…

The defaults are bad, but these models are highly steerable. For simple scripts adding to the prompt something like "do not over engineer, do not gold plate, no CLI args, keep it simple" does wonders. For whole projects, I have a 3 page anti-bloat.md which describes what not to do, stuff like: > Minimize lines of code, number of files, classes, protocols, factories, wrappers, and dependency-injection objects. Prefer…

> For whole projects, I have a 3 page anti-bloat.md which describes what not to do

This line would be cut from a satire for being too heavy-handed.

Re: OpenAI begins rolling out GPT-6 Astra

#270

Post by ankarhem »

zzleeper wrote: post #14

(Posting partly so I can revisit my predictions when they open access more widely) A big problem I have with OpenAI's models (and of course Claude) is that they tend to write the most over-engineered pieces of code, beyond the imagination of any architecture's astronaut. Just this week I asked 5.6-sol-ultra to update a 1000 LOC python script I had, to "incorporate the key lessons learned when using it for another pro…

Add something like this to your own system prompt:

Remember the golden rule; compression is intelligence. Derive rules from facts that dictate a problem to create an elegant solution. Less is more.

Post reply on HN