Under current case law (Carpenter and recently affirmed in Chatrie) it will definitely be a search, IMO it is just when the sensors become dense enough according to the court (absent states do not make regulation themselves to require a warrant for historical data).
Great; it would be good to have a precedent. (The one you picked, [6], is indeed a blazing case.) And good luck with your business; it is very much welcomed!
This is what the majority of mine look like as well. Just simple instructions for things I need to do repeatedly.
I have not even really needed a formal memory system. If I see an error happen more than once, I just say "hey add a note on this to agents.md". Tends to be verbose but overall works quite well for the projects I am doing.
Is there a good example someone can show of naturally generating real videos using extending and interpolation from the last frames? (For any of the video generators).
I mean I have not tinkered that much, but trying to even get a video to 30 seconds (I just want a cartoon AI avatar to narrate tutorials) has been incredibly difficult. They drift so easily.
Many AI videos you can tell just stitch short clips together. I just want a continuous scene for like 30 seconds to 2 minutes.
This is another riff on not embedding a full document, but doing a summarization of the document and embedding the summary for RAG. Nice usecase for high cardinality data!
I did not know about this when I wrote https://andrewpwheeler.com/2026/08/12/license-plate-reader-s... the day prior, but one of the things I did state was deleting data (except in the extreme case, like New Hampshire's 3 minute retention), will not prevent abuse. People just do illegal queries over and over again.
Part of the reason I wrote that post is it is better to retain the data indefinitely and have a warrant standard than continue to reduce the time period in which the data is retained.
This is already the current status quo on paper. I bet the majority of the cases IJ identified of mis-use the PDs already had this policy. (That is the same standard when you do a background criminal history check in New York, need to put in a case number, FYI.)
I did not want to go into too many technical details on the post -- I think you could do an AI audit at the point in time of the search query to prevent people putting in junk cases. That said I believe there will always need to be third party audits at a minimum.
Part of the issue is policies on paper are not effectively enforced. So people saying "just have policy X to prevent abuse" is a non-answer.
I wrote the post mainly because people arguing for limited data retention I think is bad for both sides -- it neither protects civil liberties and simultaneously makes it harder for long term criminal investigations.
It isn't at all the current status quo. There may be some kind of departmental guideline in some cases, but it's neither required by the software, nor mentioned in the Lexipol Media Group policy template that commonly gets purchased by police departments once the public starts asking them what their ALPR policy is. A quick spot-check of eyesonflock.com finds that, of those audit logs that are still available to the public, case or CAD IDs are still not commonly required.
The thing about CAD/case IDs is that it makes the use of junk cases in audit trails more detectable vs. the current situation.
Third-party audits would be great, but I haven't been able to find an ideal third party to do the auditing. Locally, police commission groups quickly got co-opted through political processes into being both toothless and extremely deferential towards the police department. I wouldn't trust state auditors any more than local auditors. That's why we pushed to force audit logs to be made publicly accessible in SB1516 6(3)(a): https://olis.oregonlegislature.gov/liz/2026R1/Downloads/Meas...
> Part of the issue is policies on paper are not effectively enforced. So people saying "just have policy X to prevent abuse" is a non-answer.
Policies on paper are where you start. I wholeheartedly agree that they are not by themselves sufficient, but they have to exist, and to that end, you want the strictest possible policies that are politically achievable. I don't believe that a warrant requirement is politically achievable.
We had several deep conversations with ACLU on data retention limits. Data retention limits were one of the things they fought hardest for in this state. We supported that, but focused more of our energy on a different aspect (which we didn't succeed at, unfortunately). ACLU's point of view is that longer data retention makes it easier to profile the movements and activities of politically sensitive groups. It's true that it does, but ALPR vendors' ability to directly access and control the data means that there are numerous trivial workarounds for targeting any demographic or political group, regardless of data retention limits.
I remain of the opinion that these systems simply don't need to exist at all, which makes the answers to a lot of these questions a lot easier. Violent crime has overall been trending downward for a long time, we live in one of the most peaceful societies in human history, we already know how to reduce property crime and crime directly related to poverty, and roving armed gangs are not a sensible immigration policy. We're twisting ourselves in knots trying to figure out how to make an inherently unsafe technology safe to meet a need that we don't have.
Flock exists because YCombinator and subsequent investors saw an opportunity to use public grant money to pay to bootstrap the collection of an enormous amount of really valuable data on Americans.
I cannot read this article, but this may be partly confused what this function by Carbyne does. If there is a flood of critical systems, it just plays an auto message "If this is about X, thank you and we know about it" if you called from the same area.
I don't remember from prior articles if at that point you just stay on the line, or if you need to press a button. It is not going through an AI voice call tree.
It says its main function is to recognize if the call is related to a previous incident already registered. If it is, then the AI provides an update on the matter, otherwise it directs the caller to a human
My experience like this was for a data scientist position at Facebook in 2022.
So the question was something like, here is a table of predicted probabilities for credit card transactions (hypothetical table, I do not remember the exact quantities), but it looked something like this:
And then the question was "what was the threshold used to maximize (precision|recall)?" (I cannot remember which metric they were asking for).
My response was that a proper decision model should take the dollar amount of the transaction into consideration, so the decision should more like be `$*p > threshold`, where this threshold meets your precision and recall for preventing dollars lost instead of the binary yes/no.
The interviewers English was not great, so after all that I was just like "well to answer your exact question, it could be anywhere between `0.5 < p <= 0.7`"
At one point earlier in my career (during the early 2000s), they flew me to Chicago, picked me up in a limo and gave me a tour of the office... I knew I didn't want to relocate (from the East Coast) and remote work wasn't an option back then, so I had nothing to lose... They asked me the question of "4 lightbulbs in a room down the hallway, with 3 light switches in the room I'm in" to tell which switch belonged to which bulb...
I went in totally unprepared for logical tests, and flubbed the perfect answer partially, but it was funny because I asked the guy if I was "doing an interview to be an electrician or a software developer?".
Since then I've been just fine, and to this day, I've never had to answer that question nor use that type of logic on any job... I reverse engineer & migrate major software apps all the time as a Solutions Architect & Development Director.
I've always found interviews that involve behavioral and cognitive tests to never be good for me as long-term jobs... Now I interview & hire people regularly without asking those types of questions at all because the questions can too easily be studied & rehearsed prior to interviews.
Under current case law (Carpenter and recently affirmed in Chatrie) it will definitely be a search, IMO it is just when the sensors become dense enough according to the court (absent states do not make regulation themselves to require a warrant for historical data).
reply