I get what you're saying, but looking at some examples, they look kinda of right, but there are a lot of misleading facts sprinkled, making his grading wrong. It is useful, but I'd suggest to be careful to use this to make decisions.
Some of the issues could be resolved with better prompting (it was biased to always interpret every comment through the lens of predictions) and LLM-as-a-judge, but still. For example, Anthropic's Deep Research prompts sub-agents to pass original quotes instead of paraphrasing, because it can deteriorate the original message.
Some examples:
Swift is Open Source (2015)
===========================
sebastiank123 got a C-, and was quoted by the LLM as saying:
> “It could become a serious Javascript competitor due to its elegant syntax, the type safety and speed.”
Now, let's read his full comment:
> Great news! Coding in Swift is fantastic and I would love to see it coming to more platforms, maybe even on servers. It could become a serious Javascript competitor due to its elegant syntax, the type safety and speed.
I don't interpret it as a prediction, but a desire. The user is praising Swift. If it went the server way, perhaps it could replace JS, to the user's wishes. To make it even clearer, if someone asked the commenter right after: "Is that a prediction? Are you saying Swift is going to become a serious Javascript competitor?" I don't think its answer would be 'yes' in this context.
How to be like Steve Ballmer (2015)
===================================
Most wrong
----------
> corford (grade: D) (defending Ballmer’s iPhone prediction):
> Cited an IDC snapshot (Android 79%, iOS 14%) and suggested Ballmer was “kind of right” that the iPhone wouldn’t gain significant share.
> In 2025, iOS is one half of a global duopoly, dominates profits and premium segments, and is often majority share in key markets. Any reasonable definition of “significant” is satisfied, so Ballmer’s original claim—and this defense of it—did not age well.
Full quote:
> And in a funny sort of way he was kind of right :) http://www.forbes.com/sites/dougolenick/2015/05/27/apple-ios...
> Android: 79% versus iOS: 14%
"Any reasonable definition of 'significant' is satisfied"? That's not how I would interpret this. We see it clearly as a duopoly in North America. It's not wrong per se, but I'd say misleading. I know we could take this argument and see other slices of the data (premium phones worldwide, for instance), I'm just saying it's not as clear cut as it made it out to be.
> volandovengo (grade: C+) (ill-equipped to deal with Apple/Google):
>
> Wrote that Ballmer’s fast-follower strategy “worked great” when competitors were weak but left Microsoft ill-equipped for “good ones like Apple and Google.”
> This is half-true: in smartphones, yes. But in cloud, office suites, collaboration, and enterprise SaaS, Microsoft became a primary, often leading competitor to both Apple and Google. The blanket claim underestimates Microsoft’s ability to adapt outside of mobile OS.
That's not what the user was saying:
> Despite his public perception, he's incredibly intelligent. He has an IQ of 150.
>
> His strategy of being a fast follower worked great for Microsoft when it had crappy competitors - it was ill equipped to deal with good ones like Apple and Google.
He was praising him and he did miss opportunities at first. OC did not make predictions of his later days.
[Let's Encrypt] Entering Public Beta (2015)
===========================================
- niutech: F "(endorsed StartSSL and WoSign as free options; both were later distrusted and effectively removed from the trusted ecosystem)"
Full quote:
> There are also StartSSL and WoSign, which provide the A+ certificates for free (see example WoSign domain audit: https://www.ssllabs.com/ssltest/analyze.html?d=checkmyping.c...)
>
> pjbrunet: F (dismissed HTTPS-by-default arguments as paranoid, incorrectly asserted ISPs had stopped injection, and underestimated exactly the use cases that later moved to HTTPS)
Full quote:
> "We want to see HTTPS become the default."
>
> Sounds fine for shopping, online banking, user authorizations. But for every website? If I'm a blogger/publisher or have a brochure type of website, I don't see point of the extra overhead.
>
> Update: Thanks to those who answered my question. You pointed out some things I hadn't considered. Blocking the injection of invisible trackers and javascripts and ads, if that's what this is about for websites without user logins, then it would help to explicitly spell that out in marketing communications to promote adoption of this technology. The free speech angle argument is not as compelling to me though, but that's just my opinion.
I thought the debate was useful and so did pjbrunet, per his update.
I mean, we could go on, there are many others like these.
I understand the exercise, but I think it should have a disclaimer, some of the LLM reviews are showing a bias and when I read the comments they turned out not to be as bad as the LLM made them. As this hits the front page, some people will only read the title and not the accompanying blog post, losing all of the nuance.
That said, I understand the concept and love what you did here. By this being exposed to the best disinfectant, I hope it will raise awareness and show how people and corporations should be careful about its usage. Now this tech is accessible to anyone, not only big techs, in a couple of hours.
It also shows how we should take with a grain of salt the result of any analysis of such scale by a LLM. Our private channels now and messages on software like Teams and Slack can be analyzed to hell by our AI overlords. I'm probably going to remove a lot of things from cloud drives just in case. Perhaps online discourse will deteriorate to more inane / LinkedIn style content.
Also, I like that your prompt itself has some purposefully leaked bias, which shows other risks—¹for instance, "fsflover: F", which may align the LLM to grade worse the handles that are related to free software and open source).
As a meta concept of this, I wonder how I'll be graded by our AI overlords in the future now that I have posted something dismissive of it.
If someone is reading this and is getting demotivated to apply yourself to any field that you like because you think you don't have the skills, please, don't. Parent isn't saying that you shouldn't try. We're usually terrible to estimate our own abilities. How many times you thought you were incapable of doing something and you end up doing it?
My own anecdotal example. I stopped playing music years ago because I thought I wasn't good, despite liking it. I started playing again because I had no games and I noticed that I should have gotten back to it sooner, despite not being music material. Not only I was able to play stuff that I liked, I learned stuff that I thoroughly enjoyed. Some music were really hard at first, but as I progressed (very) slowly through weeks, I could see my skills improving and I was very satisfied to watch it (slow as it was).
If you like it, I think you should do it, despite of others. Because it won't matter, in the end. It may take time and a lot of effort, can be painful, but it's worth it.
Thanks, you're totally right to point this out. One should no more give up music because of the geniuses out there than one should stop playing golf or basketball because becoming Tiger Woods or Michael Jordan isn't going to be just a matter of practicing hard.
Most adults overestimate how fast they should improve in the short term and really underestimate how far they can get by just practicing regularly and consistently over many years.
You're considering that everyone watching this video knows who styropyro is and have watched all his past videos, including the ones with safety instructions (which may sound like a waste of time to some people with other cooler videos to watch). This looks like the curse of knowledge at play, because there is a demographic that may think it's fine to try this at home. My suggestion would be to simply include more visual disclaimers, because his presentation makes it look like it isn't dangerous, despite him warning sometimes (but always half joking). The current disclaimers are easily missed since there are some people who skip the video to the good parts and don't watch everything.
And just making clear that I want him to keep the jokes (like the moment at 3:20). Those are the best parts. ElectroBOOM does stuff like that too and it's great, but I think it conveys better how painful/dangerous it is. Perhaps if he includes an intro where he warns without jokes, and then adds some visual warnings throughout the video, would be enough. For instance, in this joke, it wasn't shown to a newcomer what he did to ensure it's safe to poke the microwave around like that.
I share the sentiment, but I noticed that sometimes I use it as an excuse for not doing what I can within my reach. One benefit I see with individual action is that it's a way to stimulate political change (another one being economical). Plus, it may be contagious and make changes for the next generations. Thus, nothing prevents us from adopting bidirectional planning, i.e., both top-bottom (political, schools, etc.) and bottom-up (individual). It intuitively seems faster than top-bottom only.
I'm one of those incongruent persons. Being wary of many VPN services, I never committed to using one, although I really wanted to start. Of course, I am aware of Mullvad and I could still skip the intermediary. However, I trust Mozilla more, as I've been following them for so long.
It sounds funny, because I do acknowledge exactly what you're saying. I'm in tech, interested in using VPN for years. I researched some, but was put off if they would mishandle my data. In the end, it will be Mullvad who will be dealing with my data, after all. But now I kinda trust them more after Mozilla.
I know it sounds illogical, just explaining how I feel about this.
You are Trump, a peasant living in the kingdom of Larion. You have a pitchfork
and a nothing else. You wake up and begin working in the fields. You see your
brother, who is also named Donald. He has a wife and two children. One day he
tells you that he wants to marry his sister. You think it's stupid, but you
agree. Your brother marries her and you become their neighbor
Same approach, they also pretended to be from the bank calling about an irregular transaction. In this scam, it seems they hijacked her home phone line. She tried to call from her cell phone, then they called back to her home phone and said all communication should be from it, to ensure she was at a different location.
Some of the issues could be resolved with better prompting (it was biased to always interpret every comment through the lens of predictions) and LLM-as-a-judge, but still. For example, Anthropic's Deep Research prompts sub-agents to pass original quotes instead of paraphrasing, because it can deteriorate the original message.
Some examples:
sebastiank123 got a C-, and was quoted by the LLM as saying: Now, let's read his full comment: I don't interpret it as a prediction, but a desire. The user is praising Swift. If it went the server way, perhaps it could replace JS, to the user's wishes. To make it even clearer, if someone asked the commenter right after: "Is that a prediction? Are you saying Swift is going to become a serious Javascript competitor?" I don't think its answer would be 'yes' in this context. Full quote: "Any reasonable definition of 'significant' is satisfied"? That's not how I would interpret this. We see it clearly as a duopoly in North America. It's not wrong per se, but I'd say misleading. I know we could take this argument and see other slices of the data (premium phones worldwide, for instance), I'm just saying it's not as clear cut as it made it out to be. That's not what the user was saying: He was praising him and he did miss opportunities at first. OC did not make predictions of his later days. Full quote: Full quote: I thought the debate was useful and so did pjbrunet, per his update.I mean, we could go on, there are many others like these.
reply