Additional description here: https://x.com/michaelandregg/status/2030764512488677736

Comments URL: https://news.ycombinator.com/item?id=47319511

Points: 4

# Comments: 2

Comments URL: https://news.ycombinator.com/item?id=47200088

Points: 3

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47190425

Points: 5

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47161823

Points: 1

# Comments: 0

https://news.ycombinator.com/item?id=46793253

I imagined, at the time, future goals would be to scale store size and product variety while reducing the cost of the technology, but I have no insight into how that progressed. I am sorry to learn it's been shut down.

It is unlikely the tech would be frozen when an acceptable accuracy threshold is reached:

1. There is a strong incentive to reduce operational costs by simplifying the hardware infrastructure and improving the underlying vision tech to maintain acceptable accuracy. You can save money if you can reduce the number and quality of cameras, eliminate additional signal assistance from other inputs (e.g., shelves with load cells), and generally simplify overall system complexity.

2. There is business pressure to add product types and fixtures which almost always result in new customer behaviors. I mentioned coffee in my prior post. Consider what it would mean to add support for open-top produce bins and the challenge of complex customer rummaging. It would take a lot of high-quality annotated data and probably some entirely new algorithms, as well.

Both of those require maintaining a well-staffed annotation team working continuously for an extended time. And those were just the first two things that come to mind. There are likely more reasons that aren't immediately apparent.

[Disclaimer: Former Amazon employee and not involved with Go since 2016.]

I worked on the first iteration of Amazon Go in 2015/16 and can provide some context on the human oversight aspects.

The system incorporated human review in two primary capacities:

1. Low-confidence event resolution: A subset of customer interactions resulted in low-confidence classifications that were routed to human reviewers for verification. These events typically involved edge cases that were challenging for the automated systems to resolve definitively. The proportion of these events was expected to decrease over time as the models improved. This was my experience during my time with Go.

2. Training data generation: Human annotators played a significant role in labeling interactions for model training-- particularly when introducing new store fixtures or customer behaviors. For instance, when new equipment like coffee machines were added, the system would initially flag all related interactions for human annotation to build training datasets for those specific use cases. Of course, that results in a surge of humans needed for annotation while the data is collected.

Scaling from smaller grab-and-go formats to larger retail environments (Fresh, Whole Foods) would require expanded annotation efforts due to the increased complexity and variety of customer interactions in those settings.

This approach represents a fairly standard machine learning deployment pattern where human oversight serves both quality assurance and continuous improvement.

The news story is entertaining but it implies there was no working tech behind Amazon Go which just isn't true.

Comments URL: https://news.ycombinator.com/item?id=46571404

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=46461407

Points: 7

# Comments: 2

Comments URL: https://news.ycombinator.com/item?id=46418122

Points: 1

# Comments: 0

There Ain’t No Such Thing as the Fastest Code: Lessons Learned in the Pursuit of the Ultimate Word Counter

Article: https://www.phatcode.net/res/224/files/html/ch16/16-01.html

Code: https://www.phatcode.net/res/224/files/html/ch16/16-05.html

Comments URL: https://news.ycombinator.com/item?id=44534942

Points: 1

# Comments: 0

I worked on the first iteration of Amazon Go in 2015/16 and can provide some context on the human oversight aspects.

The system incorporated human review in two primary capacities:

1. Low-confidence event resolution: A subset of customer interactions resulted in low-confidence classifications that were routed to human reviewers for verification. These events typically involved edge cases that were challenging for the automated systems to resolve definitively. The proportion of these events was expected to decrease over time as the models improved. This was my experience during my time with Go.

2. Training data generation: Human annotators played a significant role in labeling interactions for model training-- particularly when introducing new store fixtures or customer behaviors. For instance, when new equipment like coffee machines were added, the system would initially flag all related interactions for human annotation to build training datasets for those specific use cases. Of course, that results in a surge of humans needed for annotation while the data is collected.

Scaling from smaller grab-and-go formats to larger retail environments (Fresh, Whole Foods) would require expanded annotation efforts due to the increased complexity and variety of customer interactions in those settings.

This approach represents a fairly standard machine learning deployment pattern where human oversight serves both quality assurance and continuous improvement.

The news story is entertaining but it implies there was no working tech behind Amazon Go which just isn't true.

Comments URL: https://news.ycombinator.com/item?id=43895844

Points: 6

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=43723794

Points: 4

# Comments: 0