Amazon saves millions by replacing Sonnet 4.6 with Strands Decider

oofbey

If their model costs 98% less than Sonnet, and Amazon is saving “millions” then these folks are raking in 2% of millions. Congrats I guess?

sznio

why didn't they upgrade to further sonnet versions?

coolgoose

Yea right... Paying market price of 3 usd per mil tokens on sonnet 4.6...

armcat

About six years ago we built a ticket classification/routing model and pipeline [1]. The initial version was trained using SVMs, it took a couple of minutes to train, and the ticket classification was just a few milliseconds. It's so fascinating to watch how the field moved over to LLMs, and then back to faster/cheaper classifiers again. [1] "Linnaeus: A highly reusable and adaptable ML based log classification pipeline", https://arxiv.org/abs/2103.06927 NOTE: the work was actually accepted at the International Conference on Software Engineering (ICSE) in 2021.

phillennium

It's funny how AI sometimes feels like it went full circle: — "Let's build efficient classifiers" — "Forget about the silly classifiers, LET'S BUILD A MACHINE GOD" — "Ah, that machine god is often too expensive and underwhelming. Let's build efficient classifiers"

Kaedon

At ~$21,700 saved per million tickets, saving millions annually would suggest at least 92 million tickets a year to reach $2 million saved. Is that about right? I initially thought of tickets as just customer support, or internal JIRAs, but the article mentions alarms, security findings, and capacity increase requests, so that makes the scale feel more plausible. Still surprising so many tickets go through the system.

tdhz77

You can do this even more efficiently with the rust crate bonsai. You will have more control and you can create sceneries of logic. You can use incredibly cheap models this way and get way better results. I built a real time character story. In which players interact and integrate fictional characters. There is no delay in response and the characters are all in character. Oh and it’s all voice. It’s shocking how effective this is.

lencastre

counting the miliseconds until the insurance industry picks this up

3eb7988a1663

Classifying into one of 20 groups? Did anyone try scikit learn?

nlpnerd

Founder of Seldon AI (www.seldon-ai.com) here. We are working on dev tools to help developers with this kind of refactoring and continual production work. Basically there is a whole host of tarpit usage of LLMs in application backends today. This is simply another case of LLMs enabling people to build what they cannot productionize or maintain. Today developers without any AI/ML skillset can prototype a fancy new feature with LLMs, what used to require collecting and curating data to train a pipeline of ML models then serving them in production. The problem comes when it's time to take the new feature into production. That $20 cost with prototype/beta workload is now $30k per month in LLM costs, and those hallucinations that never happened on their 200 test samples is happening 600 times per day. They are then stuck, because they lack the knowledge and budget to build and run the production ML pipeline properly, the infra stack necessary to handle production workload. Management also doesn't understand why they have to invest in rebuilding something that "seems to work" with "outdated methods". These system one or decision models are a step up from LLMs when it comes to this usage. Problem is that they are still difficult to work with (limited in expression power) for many application logic. Despite the initial popularity, I hear about a lot of frictions refactoring LLM based backend with them, and multiple cases of production rollbacks to LLMs already. I think system one models is a sensible paradigm, and we are on the precipice of something great, but there is a lot more work needed above the model layer to make this work.

hubertzhang

People use machine learning models before and after LLM is invented.

cmiles8

This pattern is playing out a lot. Running LLM inference at scale on apps typically lacks ROI. But I increasingly see folks use LLMs to help improve classical techniques. So there’s some LLM use to develop a new version of algo, but maybe 2% of what would have been used by putting LLMs in the path of every API call. That generally does have ROI. Putting LLMs in the loop each time is generally a dumb move, unless you’re an AI bro trying to get everyone to use LLMs for all the things.

psnehanshu

Ok, but why did they chose Sonnet in the first place? Couldn't they have chosen Haiku or GPT Luna or maybe even some small cheap Chinese model?

llukas

Are developments like that priced in Anthropic IPO?

nikit1411

yah i mean older models dosent mean they are worthless i still use cluade opus 4.6 for day to day task

speedboat199

Meanwhile they could have just switched to Haiku 5.5 to get same savings. No need for complex orchestration involving GPU instances and would have just been a one line change in the code.

Oras

Nice marketing to sell their decision model.

gvv

What I don't understand is why are they not offering the decision model via Bedrock yet. Sagemaker / Lambda are quite expensive if you're not using the model continuously.

Gasp0de

This article is so confusing. For example, they say they tried the Strands Decider model and dismissed it for Gemma, then they continue to call the model they used Strands Decider? Did I miss something?

egorfine

> JSON key order changed the answer. Sending the same content with keys in a different order moved the output probabilities by up to 0.19 Isn't it detrimental?