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

A Japanese company cut 80% of the time needed to manually count pearls

countthings.com

Post reply on HN
Print view View original

111–120 of 236 posts

Re: A Japanese company cut 80% of the time needed to manually count pearls

#111

Post by rationalData »

distribot wrote: post #74
temporalparts wrote: post #6

Wow, this is such a simple application of ML and it is incredibly valuable. On their website, they charge $100/month per device or $1000/year per device [0] and I bet they're making a killing. [0] https://countthings.com/en/

I wish I could get a bead on how useful ML is. Hackernews makes me think it’s all hype.

It's literally statistics applied to data.

If your data is good and you can fit it to a model it will work.

The problem is that data is often poor and the idealized models don't fit real world conditions so you can have problems like overfitting.

Re: A Japanese company cut 80% of the time needed to manually count pearls

#112

Post by rationalData »

smichel17 wrote: post #81
distribot wrote: post #74

Earlier quoted context omitted.

I wish I could get a bead on how useful ML is. Hackernews makes me think it’s all hype.

The main reason I'm trying to cut down on my HN consumption a bit is the incessant pessimism. While a regular reality check is definitely useful, the "I'm so jaded by everything" vibe makes it hard to get excited about anything. I like being excited by things! It feels good and motivates me. Too much HN is a recipe for lethargy.

I think the most important reason to reduce consumption is due to everything being carefully curated.

Actual issues from a particular fruit company like the butterfly keyboard was cause of getting flagged, you weren't allowed to talk about it. Similar problems happen to this day.

Re: A Japanese company cut 80% of the time needed to manually count pearls

#113

Post by leucineleprec0n »

BorisTheBrave wrote: post #98
morsanu wrote: post #39

Earlier quoted context omitted.

For most of our clients, we get to 100% accuracy. For some more difficult scenarios, a lower accuracy is ok for estimations (e.g. estimating the crop in agriculture). It's also super easy to correct mistakes or to add items that are not visible in the image.

You don't mean 100% accuracy, that means mistakes are impossible. Perhaps your error rate is very rare, but it's a bit concerning you don't attempt to quantify it.

Suppose it depends on which part of the chain he attributes error, plausible lighting or poor positioning - anything that is an employee duty - does throw it off and then they scrub it. But yeah. Still.

Re: A Japanese company cut 80% of the time needed to manually count pearls

#114

Post by antattack »

morsanu wrote: post #14

Hi, there! I'm one of the project managers at CountThings, I'll try to respond to comments here but I guess you can AMA.

It seems to me that it would be useful for the app to count items on the left and right of a ruler (or some line) so correct number of items can be separated out from a pool.

Re: A Japanese company cut 80% of the time needed to manually count pearls

#115

Post by iagovar »

BiteCode_dev wrote: post #99
distribot wrote: post #74

Earlier quoted context omitted.

I wish I could get a bead on how useful ML is. Hackernews makes me think it’s all hype.

I don't know about others, but because a lot of IT news comes to me from American medias, I _always_ consider it hype. The reason is cultural: american can't seem to do without superlatives. They didn't eat good carrots yesterday, there were AMAZING carrots. They don't introduce me to their friends, but to their VERY BEST friends. They are always EXCITED to do X and SO something about Y. The result is that none of th…

But americans do get marketing though. I bet you know about a bunch of companies that were doing $thing in $country before, probably with better outcomes, but never got the recognition.

In Spain, for example, many industrial companies have a culture where marketing is nearly BS. That hurts them a lot IMO.

Re: A Japanese company cut 80% of the time needed to manually count pearls

#116

Post by JackFr »

bonoboTP wrote: post #88
distribot wrote: post #74

Earlier quoted context omitted.

I wish I could get a bead on how useful ML is. Hackernews makes me think it’s all hype.

Depends on your baseline excitement. If you're so hyped up that you think it can classify bad and good prospective employees from a single photo, you should tone it down because that's nonsense. If you think it's all fluff, then you are also wrong. There are many great ML applications for constrained scenarios. But this pearl counting does not require modern ML at all. It can be done with decades old image processing…

There’s also a technique called “weighing”.

It’s a transformation which, by assuming the items are identical, turns quantity from a discrete value to a continuous one with some loss of precision. In many cases measurement times can be reduced my more than 99%.

Re: A Japanese company cut 80% of the time needed to manually count pearls

#117

Post by iagovar »

morsanu wrote: post #106
MichelSr wrote: post #102

Earlier quoted context omitted.

What's the rate nowadays for devs in Romania? ~ $1k/month?

It really depends on the city and the type of business. Bucharest wages are higher. Btw, we are not an outsourcing company. Everything is done in Romania: development, sales, management.

Having an US office is due to business needs?

Re: A Japanese company cut 80% of the time needed to manually count pearls

#118

Post by ethbr0 »

iagovar wrote: post #115
BiteCode_dev wrote: post #99

Earlier quoted context omitted.

I don't know about others, but because a lot of IT news comes to me from American medias, I _always_ consider it hype. The reason is cultural: american can't seem to do without superlatives. They didn't eat good carrots yesterday, there were AMAZING carrots. They don't introduce me to their friends, but to their VERY BEST friends. They are always EXCITED to do X and SO something about Y. The result is that none of th…

But americans do get marketing though. I bet you know about a bunch of companies that were doing $thing in $country before, probably with better outcomes, but never got the recognition. In Spain, for example, many industrial companies have a culture where marketing is nearly BS. That hurts them a lot IMO.

Both of these are interrelated.

I think one of the reasons Americans overuse superlatives is because they're constantly bathed in expensive marketing.

Consequently, everyone is used to being told everything is good / great / the best. Which means anyone actually expressing that in a human capacity has to reach for "the very best" or similar.

Re: A Japanese company cut 80% of the time needed to manually count pearls

#119

Post by ethbr0 »

rationalData wrote: post #112
smichel17 wrote: post #81

Earlier quoted context omitted.

The main reason I'm trying to cut down on my HN consumption a bit is the incessant pessimism. While a regular reality check is definitely useful, the "I'm so jaded by everything" vibe makes it hard to get excited about anything. I like being excited by things! It feels good and motivates me. Too much HN is a recipe for lethargy.

I think the most important reason to reduce consumption is due to everything being carefully curated. Actual issues from a particular fruit company like the butterfly keyboard was cause of getting flagged, you weren't allowed to talk about it. Similar problems happen to this day.

Mac fans being rabid Mac apologists isn't something leaving HN is going to change.

Re: A Japanese company cut 80% of the time needed to manually count pearls

#120

Post by jmmcd »

BorisTheBrave wrote: post #98
morsanu wrote: post #39

Earlier quoted context omitted.

For most of our clients, we get to 100% accuracy. For some more difficult scenarios, a lower accuracy is ok for estimations (e.g. estimating the crop in agriculture). It's also super easy to correct mistakes or to add items that are not visible in the image.

You don't mean 100% accuracy, that means mistakes are impossible. Perhaps your error rate is very rare, but it's a bit concerning you don't attempt to quantify it.

I disagree. If we consider a single customer with a particular application, we probably imagine an iterative process like this: the customer supplies some sample images, the system gets a few wrong, they add special cases, fine-tune the hyperparameters, whatever, and after all this they literally get 100% on the customer's holdout data. If that happens for several customers then the GP statement is justified (no other number is possible for these customers).

Possibly you're thinking of a single error rate across all customers? For other customers, as stated, it's not 100%. But taking an average across multiple customers is not meaningful when some are counting pearls and some are counting crops.

Post reply on HN