Hacker News new | past | comments | ask | show | jobs | submit
Otterly99 | on: Amazon saves millions by replacing Sonnet 4.6 with Strands Decider
It's baffling to me that a company like Amazon would choose to use a LLM for a task as simple as ticket classification. Don't they have thousands of engineers and petabytes of data? They even have their Mechanical Turk program if they want a cheap labelling workforce.
dansalvato | parent | next
Ticket classification isn't necessarily so simple, and I can think of various reasons for using ML to classify tickets.

1. Some auto-generated ticket (e.g. a trigger from unusual hardware activity or a log entry) resembles a previous ticket that had meaningful action on it, addressed and solved by a specific team. That ticket could spend a week getting ignored or punted around when the right team can solve it in 5 minutes. ML could detect the similarity and reclassify it by that metric. 2. Human-submitted tickets are annoyingly fallible. For example, an "I can't log into my account" ticket could be auto-classified as "account recovery". Or maybe, e.g. the ticket system attaches a recent activity log from that IP address to be cross-checked by ML, which finds 5xx errors and reclassifies it for the technical team.

These are generic examples, but you can use your imagination and see how a company as huge as Amazon could benefit from this. I think it's for the purpose of minimizing the number of tickets that need to be manually reclassified because the wrong info was given to the wrong person.

infecto | parent | next
I thought MT was being deprecated if not already?

It’s not that baffling Amazon has something like 70k+ engineers worldwide. Never worked there myself but in large orgs things sometimes get lost in the shuffle.

I don’t think timelines were shared but this reads like a pretty good case of building an MVP and then lowering the cost once it’s proven. One of the whole value props for LLMs from a ML perspective is being able to get something out the door a lot quicker than you would otherwise.

fusslo | parent | next
I'd love some classification for support tickets where i work

whenever i submit a ticket (need hardware, problem with software, access, etc etc) I'm supposed to know what business unit im submitting to. There are 63 last time I checked. Some go to global IT. some go to local IT. some go to to procurement, etc etc. There's no resources on how to select the right one

I just guess and there is a dedicated person on every team who reassigns tickets to the right business unit.

nightmare.

an llm that parses my request and auto-populates in the back end would be cracker jack

iLoveOncall | parent | next
As someone working on tickets at Amazon, it's absolutely not straightforward at all and even an LLM (or a human!) will struggle.
QuinnyPig | parent | next
They finally sunset Mechanical Turk.
TZubiri | parent
>Mechanical Turk program if they want a cheap labelling workforce.

Do we have to point out why outsourcing a task that uses client data as input (the ticket) would be a bad idea?