When I was in my 20's (about 30 years ago now, before my career in IT had began) I went to the dentist in a lot of pain. They did x-rays and said all 4 of my wisdom teeth needed to come out. It would need surgery and would cost 750 per tooth, plus the anaesthesiologist costs. I was working for a low hourly wage in the IT section of a book store at the time, and could not afford that. They then said "no probs, we also offer loans for the procedure". I went home, took some more painkillers and looked into the loan. The interest rate and term would have made it cost thousands more.
(The bookstore I worked at paid low, but had one perk I loved: they let us borrow some of the books so we could learn what was good and give advice to customers. I took the job mainly for this reason, as I was really into 3D modelling and animation and thought I could teach myself. Alas, my old 486 PC could barely run the demos.)
That week I went to my bank to see if they'd give me a loan at better rates than the dentist, and to my shock they could, and would lend me up to 5k as a personal loan, and they said I could use it for anything. I went for it and got the loan.
I didn't go back to the dentist though. Went straight to a computer store and bought one of the latest Pentium PCs and my first ever dedicated GPU (a Matrox Millennium), then stopped at the pharmacy and bought the largest pack of ibuprofen they had.
I got a dream job doing 3D modelling and animation some months after that, transitioned into multimedia programming and have been a software developer ever since, so the ROI was pretty good. And I still have all my wisdom teeth.
Fun story, but what about the pain all these years?! I'm mostly joking since I assume you'd have mentioned it if it were still there :), but I am curious if it just went away and never came back or if you found and resolved a different cause
Haha, a valid concern. I had one other episode with about the same amount of pain a few years later. I was seeing a different dentist at the time who said there was an operculum (a flap of gum tissue) over one of my wisdom teeth that was inflamed. They cleaned it, explained how to keep it clean and said they'd only remove the tooth if it happened often as it was not impacting any other teeth, didn't have cavities and the root was very close to the nerve. I just make sure to clean that area really well.
When I was studying, my pal had his wisdom tooth covered by gum completely and he had inflammation. They cut the gum and wiped puss - with teeth as well gone, so these things can happen.
I still have all wisdom teeth, even if one of them is fixed in a shape, that I can describe as a pyramid, which works for me as I do not bite on them. The other one is in better shape - it required dentists to work with "all of their hands in" and I can't open my mouth wide enough, so quite an issue to fix anything back there.
From what I understand the wisdom teeth come in horizontally, growing from the back of the jaw toward the regular back molar. Ideally, as they grow they will rotate toward the vertical. If not completely vertical when finished growing that is like a pyramid. When the wisdom tooth eventually touches the back molar without being vertical enough, that is considered impacted.
I had one that was staying horizontal, not emerging, and that might have been the only one that was pushing my other teeth closer together to where it was getting difficult to floss.
I don't have such a wide jaw either and it was a godsend that the oral surgeon was a highly dedicated South Asian having narrow palms and longer fingers than so many others, because the horizontal tooth had to be removed surgically.
Neanderthalis did not have wisdom tooth issues, and it looks like very early H sapiens did not, either.
The theory is that pre-bread societies chewed a lot more - MUCH more - and the stress induced growth in the jaw bones, which in turn made more room for the wisdom teeth to grow in straight.
I read an article about a controversial orthodontist or something, who espouses the same theory. This is why whenever skulls are found from before the industrial age, and thus before processed food was common, they have perfectly straight teeth. We were probably evolved to eat much tougher foods than we eat today.
I am 51, and about every other time I go to the dentist (same one!), he says, "you might want to think about having your wisdom teeth removed; they're only going to cause you problems."
The difference is that when I was 18, at my last pediatric dentist appointment, I was told, "keep them clean, and they'll be fine the rest of your life."
The issue with extracting teeth is that once you extract one teeth, rest of them loosens up, so better "have problems for the rest of your life" with all teeth, than different problems that comes when you have no teeth...
I'm in my 40s and most dentist office I've walked into in the last 20 years has given me "two years at most before they need to come out!!!". Last year I did end up needing only one of them to come out because of pain to the tooth next to it. The other 3 are still fine.
I can actually tell which dental office is scammy vs genuine based on their remarks on the wisdom teeth. The more adamant they are about the removal, the less trustworthy.
My wisdom teeth pushed out against all the other teeth. It was painful, they had to come out. It was a couple months too late. My lower front teeth got kinda crooked then, due to being pushed together, and still are, 20 years later.
I'm glad that worked out for you and I hope that you have no pain anymore! The tricky thing with teeth is that even a small infection can develop into a serious condition, life-threatening even, if untreated and it's hard to impossible for oneself to tell.
I never liked eggplant as a kid, but my Chinese in-laws make some amazing eggplant dishes. My favourite is one where they cut it into inch thick slices, then slice the slice about 3/4 of the way through and stuff it with a seasoned pork mince, dust it with flour and deep fry until golden.
Yeah so the other factor missing is gun calibre and ship hull reinforcement/design. The reason sloops didn’t dominate against ships of the line came down to these factors, as well as sheer number of guns.
A sloop’s guns were generally so light the balls would bounce off the hull of a ship of the line. The sheer weight of firepower in return would shred a sloop to pieces. Add on to that the fact that heavier guns can achieve longer range when trained at the right angle, and a sloop can’t really get anywhere near a ship of the line and live to tell the tale.
I plan on adding wind dynamics. The largest ship has 1 more cannon, do you think I should add more? or perhaps longer range on the larger ship cannons?
Longer range would help! I should also note that ships had forward- and aft-firing guns in addition to the main batteries on the gun decks firing to the sides. A smaller ship merely trying to run away could be fired upon until it got out of range.
This is great. I wish I had enough ram for a local model. I just spent the last few weeks writing something very similar, but I made it a local Electron app with Whisper, ffmpeg and I added semantic search and embeddings for chatting with the videos. It talks to Claude for the vision analysis, tagging and video chat. Do you only send one image for yours? I used a customised scene detection algorithm to find multiple different images per video and then send them all in one request to Claude (along with the subtitles). It's definitely the most expensive part. Using Sonnet 4.6 for the analysis and Haiku for the tagging costs about $1 for an hour of footage, I can imagine it would be slow locally.
Try some of the models on OpenRouter if you are looking to save money. Gemma 4 31B is $0.12/M input, $0.37/M output vs $1/M input, $5/M output for Haiku.
There are other options that are good too. Gemini 3.1 Flash Lite is great for this kind of thing (NOT Gemini 3.5 Flash though - the pricing for that is bad).
Cheers, I'll give it a try. How are those models at returning structured results? When I was writing the prompts for the analysis step and testing with older Claude models, it would have trouble structuring the XML consistently. Sonnet 4.6 handles it really well.
Hey, just want to thank you for this suggestion. Spent this morning swapping to open router and changing all my prompts to use tools instead of XML. Not only is Gemma and Gemini much cheaper, the output tokens from the tool call are much less too. Cost to analyse one 20 minute video with 10 snapshots went from $0.21 to $0.009, and I'm even sending full HD snapshots instead of the 960x540 ones I was sending before (to save costs). The results so far are pretty good. It looks like the larger images are giving the model more context, so in some cases making the cheaper models results better than the expensive models. I'm going to run this over a few hundred videos today and see how it goes in bulk!
Yeah, it's been awesome! I'm so excited about tool calls and function use, the possibilities are huge. I ran it over 1494 videos that range in length from a few seconds to over 3 hours. Total duration 260 hours and a total size of 3795 GB. I don't know exactly how long it took to run, as I found some bugs I needed to fix when processing mkv files, but it was probably around 24 hours in total. That wasn't all LLM requests, but also the local Whisper transcription and frame extraction / analysis. I used gemini-3.1-flash-lite-preview for the content analysis and tagging. Analysis cost $9.22 and Tagging cost $2.72 and the results seem great (for comparison, I did 885 videos a few weeks ago with Sonnet and it cost $130 in total). Gemini seems much less verbose than Sonnet, even with the same prompt, so the descriptions are much shorter, but they seem very good. The tagging is great. Another added bonus has been that with the larger screenshots being sent, the LLM can now read much more of the text it sees on screen. Some of my videos are top-down showing me drawing and writing, and now it picks that up, so it's all indexed and searchable. I tested a few models with the RAG Chat feature, and the best one so far is GPT4.1-Mini. Before, when asking questions about the library or a video it was around 4 cents each query, now its averaging about half a cent.
Not one image - 5 frames per clip, sent in a single request with a transcript snippet. So the multi-frame + subtitles in one call part is the same as yours.
But yeah, how it picks the frame is the weak-point here. Scene detection would definitely help - this is #1 on the Roadmap.
Could you share how your scene-detection picks the frames?
---
For the vector search, I went for the trade-off of not having it but keeping it simple with plain Markdown files for more portability. The knowledge travels with the files when an SSD moves, no index to keep in sync, and plain text that outlives the tool. But the other path you mentioned is interesting as well to explore.
I originally limited mine to 10 frames spread evenly throughout the video, but it missed a fair bit of context at the analysis step, and didn't scale with length. So now when a video is loaded the app extracts a bunch of frames for the entire video, then calculates an image histogram and compares similarity to the previous one. There's some configuration so it doesn't send too many to the LLM, but still gets a good cross-section of frames to send.
You could also just use FFmpeg as it can do scene detection too. I tested both but liked the results from the histogram analyzer more.
Yeah, markdown works well if you're going to search through it with Claude Code or something like that. I built ClipScape as an Electron app with a local SQLite database, as I wanted an interface I could search and chat in and see the relevant thumbnails.
But saying it's a confidence trick is saying it's a con. That they're trying to sell someone something that doesn't work. Th op is saying it makes then 10x more productive, so how is that a con?
The marketing says it does more than that. This isn't just a problem unique to LLMs either. We have laws about false advertising for a reason. It's going on all the time. In this case the tech is new so the lines are blurry. But to the technically inclined, it's very obvious where they are. LLMs are artificial, but they are not literally intelligent. Calling them "AI" is a scam. I hope that it's only a matter of time until that definition is clarified and we can stop the bullshit. The longer it goes, the worse it will be when the bubble bursts. Not to be overly dramatic, but economic downturns have real physical consequences. People somewhere will literally starve to death. That number of deaths depends on how well the marketers lied. Better lies lead to bigger bubbles, which when burst lead to more deaths. These are facts. (Just ask ChatGPT, it will surely agree with me, if it's intelligent. ;p)
How does one go about competing at the IMO without "intelligence", exactly? At a minimum it seems we are forced to admit that the machines are smarter than the test authors.
"LLM" as a marketing term seems rational. "Machine learning" also does. We can describe the technology honestly without using a science fiction lexicon. Just because a calculator can do math faster than Isaac Newton doesn't mean it's intelligent. I wouldn't expect it to invent a new way of doing math like Isaac Newton, at least.
Just because a calculator can do math faster than Isaac Newton doesn't mean it's intelligent.
Exactly, and that's the whole point. If you lack genuine mathematical reasoning skill, a calculator won't help you at the IMO. You might as well bring a house plant or a teddy bear.
But if you bring a GPT5-class LLM, you can walk away with a gold medal without having any idea what you're doing.
Consequently, analogies involving calculators are not valid. The burden of proof rests firmly on the shoulders of those who claim that an LLM couldn't invent new mathematical techniques in response to a problem that requires it.
In fact, that appears to have just happened (https://news.ycombinator.com/item?id=46664631), where an out-of-distribution proof for an older problem was found. (Meta: also note the vehement arguments in that thread regarding whether or not someone is using an LLM to post comments. That doesn't happen without intelligence, either.)
That doesn't appear to be what happened. But the marketing sure has a lot of people working quick to presume so.
I would guess it's only a matter of days before that proof, or one very similar, is found in the training data, if that hasn't happened already, just as has been the case every time.
No fundamental change in how the LLM functions has been made that would lead us to expect otherwise.
Similar "discoveries" occurred all the time with the dawn of the internet connecting the dots on a lot of existing knowledge. Many people found that someone had already solved many problems they were working on. We used to be able to search the web, if you can believe that.
The LLMs are bringing that back in a different way. It's functional internet search with an uncanny language model, that sadly obfuscates the underlying data while making guesswork to summarize it (which makes it harder to tell which of its findings are valuable, and which are not).
It's useful for some things, but that's not remotely what intelligence is. It doesn't literally understand.
>* if you bring a GPT5-class LLM, you can walk away with a gold medal without having any idea what you're doing.*
My money won't be betting on your GPT5-class business advice unless you have a really good idea what you're doing.
It requires some (a lot of) intelligence and experience to usefully operate an LLM in virtually every real world scenario. Think about what that implies. (It implies that it's not by itself intelligent.)
I didn't say anything about cheating. In fact, if it did cheat, that would make for a much stronger argument in your favor.
If scoring highly on an exam implies intelligence then certainly I'm not intelligent and the Super Nintendo from the 90s is more sentient than myself, given I'm terrible at chess.
I personally don't agree with that definition, nor does any dictionary I'm familiar with, nor do any software engineers with whom I'm familiar, nor any LLM specialists, including the forefront developers at OpenAI, xAI, Google, etc. as far as I'm aware.
But for some reason (it's a very obvious reason $$$), marketers, against the engineers' protest, appear to be claiming otherwise.
This is what you're up against and what you'll find the courts, and lawyers, will go by when this comparison comes to a head.
In my opinion, I can't wait for this to happen.
Thrilled to know if I shouldn't wait for that. If you're directly involved with some credible research to the contrary, I would love to hear more.
But IMO, in this case at least, has nothing to do with intelligence. It's performing a search against its own training data, and piecing together a response in line with that data, while including the context of the search term (aka the question). This is run through a series of linear regressions, and a response is produced. There is nothing really groundbreaking here, as best I can tell.
These arguments usually seem to come down to disagreements about definitions, as you suggest. You've talked about what you don't consider evidence of intelligence, but you haven't said anything about the criteria you would apply. What evidence of intelligent reasoning would change your mind?
It is unsupportable to claim that ML researchers at leading labs share your opinion. Since roughly 2022, they understand that they are working with systems capable of reasoning: https://arxiv.org/abs/2205.11916
Based on an English dictionary definition, I would expect an intelligence exhibits understanding, don't you? I would hope people are reading the dictionary before they market a multibillion dollar product set to reach the masses. It seems irresponsible not to.
The article you linked discussed reasoning. That's really cool. But, consider that we can say that a chess game computer opponent is reasoning. It's using a preprogrammed set of instructions to predict out to some number of possible moves ahead, and choosing the most reasonable. A calculator, essentially, it is in fact reasoning. But that doesn't have much to do with intelligence. As we read in the dictionary, intelligence implies understanding, and we certainly can't say that the Chess Masters opponent from the Super Nintendo literally understands me, right?
More to the point, I don't see that any LLM has thus far exhibited remotely any inkling of understanding, nor can it. It's a linear regression calculator. Much like a lot of TI84 graphing calculators running linear algebraic functions on a grand scale. It's impressive that basic math can achieve results across word archives that sound like a person, but it's still not understanding what it outputs, and really, not what it inputs beyond graphing it algebraically either.
It doesn't literally understand. So, it is not literally intelligent, and it will require some huge breakthroughs to change that. I very much doubt that such a discovery will happen in our lifetime.
It might be more likely that the marketers will succeed in revising the dictionary. We've seen often times that if you use words wrong enough, it becomes right. But so far at least, that hasn't happened with this word.
OK, now let's talk about what it means to "understand" something.
Let's say a kid who's not unusually gifted/talented at math somehow ends up at the International Math Olympiad. Smart-enough kid, regularly gets 4.0+ grades in normal high school classes, but today Timmy got on the wrong bus. He does have a great calculator in his backpack -- heck, we'll give him a laptop with Mathematica installed -- so he figures, why not, I'll take the test and see how it goes. Spoiler: he doesn't do so well. He has the tools, but he lacks understanding of how and when to apply them.
At the same time, the kid at the next desk also doesn't understand what's going on. She's a bright kid from a talented family -- in fact Alice's old man works for OpenAI -- but she's a bit absent-minded. Alice not only took the wrong bus this morning, but she grabbed the wrong laptop on the way out the door. She shrugs, types in the problems, and copies down what she sees on the screen. She finishes up, turns in the paper, and they give her a gold medal.
My point: any definition of "understanding" you can provide is worthless unless it can somehow account for the two kids' different experiences. One of them has a calculator that does math, the other has a calculator that understands math.
I very much doubt that such a discovery will happen in our lifetime.
So did I, and then AlphaGo happened, and IMO a few years later. At that point I realized I wasn't very good at predicting what was and was not going to be possible, so I stopped trying.
Calculators do not understand math, while both kids understand each other and the world around them. The calculator relies on an external intelligence.
Don't stop trying. Predictability is an indicator of how well a theory describes the universe. That's what science is.
The engineers have long predicted this stuff. LLM tech isn't really new. The size and speed of the machines is new. The more you understand about a topic, the better your predictions.
I'm not sure what your level of expertise is with software but I got a lot out of some free tutorials on developing your own LLM and on ML. These are even available, free, directly from Google among many other sources.
I feel that my expectations surrounding "AI" are much more realistic than they were before building the tools.
If you haven't already, it's very much worth giving them a run through.
Reading your comment made me think of the Roman generals returning to a triumph and someone constantly following them saying "memento mori", reminding them they are not a god. Now, instead of humility it would just be seen as a challenge.
An AMS is useful just so you can have 4 different filaments ready to go at any time. Doesn't need to be for multi material models. I have an A1 with the AMS lite and a Prusa mk3s, and manually changing materials is a chore.
Fair point, I don't print enough (nevermind change material often enough) that it's such a bother that I thought of it. I expected the argument to be keeping it dry, to which I'd have said a drybox and/or dehumidifier is better and (could be) cheaper.
(The bookstore I worked at paid low, but had one perk I loved: they let us borrow some of the books so we could learn what was good and give advice to customers. I took the job mainly for this reason, as I was really into 3D modelling and animation and thought I could teach myself. Alas, my old 486 PC could barely run the demos.)
That week I went to my bank to see if they'd give me a loan at better rates than the dentist, and to my shock they could, and would lend me up to 5k as a personal loan, and they said I could use it for anything. I went for it and got the loan.
I didn't go back to the dentist though. Went straight to a computer store and bought one of the latest Pentium PCs and my first ever dedicated GPU (a Matrox Millennium), then stopped at the pharmacy and bought the largest pack of ibuprofen they had.
I got a dream job doing 3D modelling and animation some months after that, transitioned into multimedia programming and have been a software developer ever since, so the ROI was pretty good. And I still have all my wisdom teeth.