I apologize for such a naive comment, as I don't have experience in this field, but I've seen OpenAI do some pretty impressive image recognition tasks (multimodal LLMs). Have you tried uploading some images of successful injection castings and some of unsuccessful injection castings (they don't even have to be of the same mold), telling it "These are examples of success" "these are examples of failures, e.g. flashing, blemish, scratch, etc" and feeding it picture(s) of the casted object?
It'd be interesting to hear how effective that is.
LLMs like GPT-4o have some pretty impressive image performance. It can actually pick up some of the more obvious defects on our buckets (Steph tested it out just now).
Two problems though with the OpenAI approach:
1. You'd need a cloud connection to send those images up to and get the answer back down so that's cost in terms of your round-trip latency, network infra, and the OpenAI account itself.
2. It doesn't do well with the very subtle defects - mild shape changes, loss of features from short shots, etc
It might be worth using in the offline pipeline for auto labeling though!
1. Many are not certain how Chinese voters impact CCP environmental policy
2. Look at per capita
3. Moving manufacturing of American goods to China can still be considered American caused emmissions, tho your stats are likely counting it as Chinese
4. The article is about the great salt lake in USA. CO2 as a global problem won't progress when everyone tries to blame everyone else
5. China is improving their efficiency. Look at electric conversion rates & cars' mpg. Americans complain about gas prices while having some of the lowest prices while driving some of the least efficient cars
Because I don't live in China and I have no way to impact Chinese climate policy. Before my government would leverage climate trade policies it'd focus on them domestically.
But beyond that, China is making WAY bigger investments into green tech than the US does. They are world leaders in battery and solar technology and production. Global transition to green energy is largely going to be thanks to Chinese investments.
Generally I agree! I saw a guy shamefully admit he didn't read the output carefully enough when using generated code (that ran), but there was a min() instead of a max(), and it messed up a month of his metrics!
Maybe a quick, cheap NeRF with some object recognition, 3D object generation and replacement, so at least you have a sink where there is a sink and a couch where you have a couch, even though it might look differently.
GP's point is that responding to an aside about how to do something with a snarky "or you could just buy a dedicated machine" will come across as obnoxious. This should be obvious to you or anyone.
It's using machine for the job, which is different than buying a machine for the job.
A hand mixer is cheap and has endless uses. A chocolate tempering machine has a single purpose. Makes sense to get one if you're making chocolate in large quantities.
A tempering machine costs hundreds of dollars and wouldn't fit in my apartment kitchen. The hand mixer was ten dollars and fits in my drawer.
Also, this is advice to anyone who wants to try it for themselves. Isn't "buy a hand mixer and some diffraction film" an easier onramp than "buy a whole tempering machine?"
I think what I’ll do is get a hobby that is not too expensive. Like, you have to buy something overpriced to satisfy a midlife crisis, but at least I will try to get some nice headphones (not harmful at least, and with nice headphones you can play your music quieter, save your hearing) or a good bicycle (healthy!) out of it.
Anything but a sports car, really. Driving around in a sports car is just advanced sitting, which I already do to much of, and they are very expensive.
Sports car does not need to be expensive. I think it's more about having a purpose and being useful rather than anything else. I saw it in me and other people I know that went through that period. The greater the thing you're working on the less you'll feel any change.
Continuing with the dev bio theme, I'd suggest kicking off a mid-life crisis with a decent microscope, petri dishes, and maybe some planeria or something else to study.
It'd be interesting to hear how effective that is.
reply