I really enjoy the balance of speed and accuracy of Astra. I can definitely see it become my driving model for most tasks, technical and non-technical.

However, I don't see it as such a massive leap compared to Fable or Sol. As ever, there's a mismatch between the benchmarks and my daily experience of the models.

What do you all think about Astra now that it's been out for a few weeks?

▲

rfgplk 6 hours ago | parent | next [-]

> What do you all think about Astra now that it's been out for a few weeks?

Best model put out so far by any of the frontier labs. Way better than Anthropics models, especially in actual text generation. Claudes fodder heavy text is ridiculous.

> However, I don't see it as such a massive leap compared to Fable or Sol.

It's hard to quantify these things without burning tons of tokens. But Fable has been a huge disappointment for me with the sole exception of graphics (UI/GPU shaders). It burns an obscene amount of tokens and barely produces output better than Opus 5.

Edit because I forgot to mention that Fable is the only modern model that seems to splat out random Chinese or Arabic glyphs. And 5.1 does it more than 5

▲

lukasbm 5 hours ago | parent | prev | next [-]

It has likely been nerfed / replaced by a cheaper version already: https://x.com/xTrinks/status/2098439889276530973 https://x.com/wholyv/status/2097985903830741439

▲

kbrannigan 6 hours ago | parent | prev | next [-]

Such a massive leap at averaging possible use cases from previous data collected.

My guess is : collect all the prompt and their satisfaction score. group them by similarity . For each group pretrain the next model on that . Get these results ready.

Next model generation feed them back those answers.

▲

mythrwy 6 hours ago | parent | prev [-]

Extremely capable and one shots large tasks from somewhat vague descriptions. Not AGI, not even close, that is complete nonsense. Just my opinion.

▲

aerhardt 6 hours ago | parent [-]

I still develop in smaller chunks, checking nearly all the output. However I have a work project (building the warehouse and BI for a client) that is well-specified and where I will try to few-shot the development. Hope it delivers.

▲

curt15 5 hours ago | parent [-]

How do you normally verify the work product of a "few-shot" development process? Do you scrutinise the source code like with human developers? Or do you just run the test suite and click around the app to check if it seems to work?

	▲	aerhardt 4 hours ago \| parent [-]
		I haven't done it in a production project - this will be the first time for me. I have specified the architecture and data definitions pretty well. The tests will be run against the customer's Excels, which is what the warehouse will be replacing. I'll check the general shape of pipelines, models, orchestration code, etc. but in many parts I probably won't review the code myself.