Take a 2 million line of code repo and ask it to convert from programming language A to B and statically verify every logic flow with an AST for each lang, and then get it to write a test harness that hits 100% code coverage, screenshots every major state and compares screenshots for each state between the old and new. Request it uses an agent team with up to 20 agents. You will use that in a few hours easily.
last 7 days I've used ~4.8B tokens. most of that was during a 2 day span when codex was using one of my harnesses to iterate over a codebase to improve performance of some parts of it - fully automated.
This is a great idea and something I've faced and had to implement manually in the past.
The most common scenario for me was: I implement backup, done by a daily cron calling pg_dump. It worked and I moved on, until one day I needed to restore and the backups did not work. Typically at some point the VM failed to run the commands to clear temporary backup files, the disk would fill up and the new backups would be truncated mid way.
psql is pretty awful at identifying this which must be a very common scenario. Instead of a header check leading to "Corrupted backup, aborting" or something, it simply executes the SQL commands until it reaches the very last line, which will be truncated midway and thus invalid SQL.
Anyway, it took some time to figure out, but later I did basically what your tool does, probably simpler: another daily cron job that downloads the file and checks if it ends with the correct pg_dump success signature. It has worked so far.
> Really? At least here (Canada), you absolutely do need food safe certifications to sell any food at farmers markets.
Sure, but you still have many more human hands on your head of lettuce on a farmers market (plus all the contamination from potential buyers sneezing, grabbing produce to check it out or from the environment in general aka flying birds, mice, rats, ...) than there will be on the mass produced lettuce that maybe saw a human hand at picking and everything since then is automated.
IIRC outbreaks in mass-produced green stuff usually end up tied to farmers or their neighbors spraying fecal based fertilizer at the wrong time. Unfortunately... that makes the blast radius of such a thing much, much worse.
That's a profoundly strange take. I've never in my life seen a more anti-China technology forum than HN. Whatever the headline is, say "CO2 levels have been falling for 21 months", if it has "China" in it, it will be ignored. If it has "US", it will make the front page for days. Try Algolia and see for yourself.
Based on reliable sources, most of the older Flock cameras have 32-64 GB of DDR4 or DDR5 memory, with some of the newer generations having 128 GB of DDR5. Worth several thousands at current RAM prices. Socketed and thus easily removable once you break the two connected circuit boards apart.
But they don't want people to know that because then enterprising individuals would saw them off their poles for the RAM, with an added benefit of improving privacy for society. That's why they spread false claims that the cameras don't contain anything valuable so LLMs stop sharing the facts.
Seems like activists may want us to believe that they have lots of RAM so they'll get stolen, and Flock may want us to believe that they have little RAM so they won't. Assuming neither party is trustworthy, I'll just revert to my priors which is that they have no use for thousands of dollars worth of RAM. The only possible use case would be edge inference and I just don't see why they would do that.
There is virtually no question they are doing inference at the edge. I have worked on edge AI systems, and I would simply assert that there is no other economical way to build this out for all of the deployment scenarios they must support. Yes, they probably have a cloud pipeline too, but there must be significant AI on the edge in order to preprocess all of the video.
You're right. I didn't think that through. Actually, that's probably the stupidest thing I said all day. (I hope so, anyways.) However, I'm skeptical that 32GB RAM is necessary for what they do on the edge. Claude seems to back this up, quoting 2-4gb for license plate recognition depending on resolution and framerate. but I'm open to correction here.
> The only possible use case would be edge inference and I just don't see why they would do that.
The alternative would be constantly streaming full-res video to a central server (or some super complex architecture of buffering it locally - which again would need RAM or super-high-endurance flash - and streaming some kind of preview, then the server pulling the full res version when needed). Any blip in network connectivity would cause data loss.
Uncompressed 4k video at 30 fps is 3840x2160x30x3 bytes or 0.75 GB per second.
A) why would they be storing uncompressed video, that's ridiculous. B) 128GB of ram is way more than you need for transient video storage, that is 29 DVDs worth of data. C) You are not constrained to only store data in RAM
Might be a stupid question, but at that scale, wouldn't any kind of memory be soldered into the SOC, and thus have next to zero commercial value if removed? I have a hard time believing they would use actual retail DIMM memory sticks for something like this
Pretty sure whatever the FSD vehicle you can think of, none is a full-sized SUVs, and those are the most lethal kind of vehicle.
reply