Hacker News Reader

Comment by EliasWatson | Hacker News Reader

To be honest, these frontier model releases have become boring for me. Opus 4.8 was already good enough for most of my use cases. I don't have any projects right now that I would use Fable for instead of Opus. So when I see announcements like this I just think "that's cool I guess" and then go back to using weaker/cheaper models.

What's far more exciting right now is models like DeepSeek V4 Flash and GLM 5.3 Flash. They have achieved good-enough-intelligence at extremely low prices and fast speeds. I don't have a use for Fable-level intelligence, but I do have uses for Opus-4.8-level intelligence that I can use as much as I want without worrying about the bill.

View on HN

The human brain is fascinating Three years ago The idea of having A robot writing production level code in 10 minutes that would have needed a team of 5 people and 2 months. Was pure Scifi

Now it's boring , not good enough

Wow there should be a term of that .

It's not that it's not good enough. It's that the cheap models are already good enough. I want a daily driver but they are trying to sell me a Ferrari. It's cool, but I have no use for it.

The term you are looking for is probably "moving the goalposts"

surely we will see all of this production code changing the world in the next two weeks like with every revolutionary new model release

Yup, i'll believe the hype when Windows doesn't suck anymore.

Maybe the hedonic treadmill fits.

It's like a form of magical realism. AI feels like straight up magic, like discovering a genie that grants wishes, but we all have bills to pay and projects to do so weeks later there's a magic lantern on every desk and the genie's doing grandma's taxes and wishing he'd stayed in the bottle.

GLM 5.3 Flash has been a relevation for me. It's practically impossible to spend more than $5-$10 per day if you're only working on a single project -- but $10 is a full-day of continuous churn. First I was super sceptical about it, and always used Fable to instruct it, but now I realised that even with complex coding, it's reasonably good.

I feel like most of the latest big Chinese lab models are good enough now. If I had to pick a difference it feels like sol goes further towards 1 shotting things and needs less babysitting. But if I am actively prompting and reading the results can get just as far on a lesser model.

I agree that intelligence at cost is exciting right now, especially if you view AI as a tool. The clock is ticking on subsidized tokens and cheap or free local inference will be the future. I think people want AI to be an oracle for prediction and discovery, which is where the sota models come in. But each release seems more iterative and underwhelming than the last. When the latest models regularly reveal unexpected insights, like how to get my execs to stop demanding hand-wavey 10x productivity gains, somebody let me know.

Not to mention you can actually see the tokens you pay for, and you can finetune it or change its system prompt.

I think compute providers are the big business. Run any model you like, adjust the weights however you like, adjust the prompts and behavior however you like, but we'll provide all of the hardware infrastructure for you at a renting fee.

I have a project that could use Fable, that fails horribly on Opus, Sol, Grok, Gemini and GLM etc, but I just can't afford to use it on something so frivolous. (Assuming Fable could complete it)

Try to solve more ambitious problems.

Something we don't actually know how to solve.

if you use these things to generate design docs / text, it should be good news if it is actually better at prose as advertised. Some people like sol for prose better the anthropic models.

fable and friends are useful for long-term agentic stuff like orchestrating glm-5.3 flash implementers and verifying them

When hn first started taking llms seriously maybe, 2-3-4 years ago (?) one of the most interesting recurring comments was that the real research goals in the field would be reducing cost, doing more with fewer parameters, making lean models, and generally improving efficiency. Of course, those research goals run counter to the need to raise capital and do massive real estate land grabs for data centers, so they are not being prioritized by the top firms running the bubble game.

Reply on news.ycombinator.com