But the older you are, the more likely it is that you have built a family and have children and responsibilities outside of work. You cannot necessarily afford to spend time studying (problems untied to the real world) as much as someone younger I guess.
I don't think its strictly a time issue, its an energy/motivation issue.
40 minutes of practice a day for a month or two should be sufficient for someone to solve/go over dozens of Leetcode questions. We all, literally all, have that time to spare otherwise we wouldn't touch our phones or ever watch T.V and yet most of us do.
But I don't disagree with you completely. I think the older you get, the more mental resistance you have to do the grind to become good at Leetcode. It just sucks that after 13 years of programming and accomplishing quite a few things I have to do this shit all over again just to get another job that's pretty much the same as I'm doing now - and this knowing that it sucks so bad - that you are reduced to a Leetcode monkey with all your experience, is quite a tough pill to swallow at 40.
I am also a bit less inclined to look for a new job in general - I have a kid, have a comfortable job with stable income (well, relatively speaking its stable) etc etc. Sure I can go try chasing FAANG salaries but the reality is for me its psychologically much more comfortable to stay where I am and it may also be sensible when calculating the risk in moving jobs.
Yea, the older I get, the less willing I am to jump through hoops, supplicate and prostrate myself in front of a company I want to work for. At 22 years old, I would have thought nothing of studying 2 hours a day, 7 days a week, for 4 weeks to get a job. Now, no way. And I believe this is a common trait among employees my age.
So if a company designs an interview process that involves all this hoop jumping and whiteboard hazing, they are deliberately adding bias against older, more experienced candidates.
> So if a company designs an interview process that involves all this hoop jumping and whiteboard hazing, they are deliberately adding bias against older, more experienced candidates.
I agree about the bias though I don't think its deliberate. I think its just the easiest way for them to filter through masses of candidates.
I recently built a small hand-wired macro pad using an Arduino Pro Micro equipped with ATmega32U4, it's apparently quite popular amongst hobbyists building custom keyboards. Quick and fun project for a beginner, the most tedious part of this project was to carve the wooden case.
Do you have a link to a PCB/kit, preferably with LEDs? Does yours run QMK? It sounds like a nice project if it costs a few bucks to get the materials, though I don't know what I'd do with it.
I didn't used a kit, but bought the components separately (microcontroller, key caps, switches, wires). It runs custom code as it was sufficient to fit my use case, though QMK may be possible? The keys are mapped from F13 to F22 and can be use in some software that allow custom keybinds.
This is great, thanks! I had researched extra F keys when I was making my keyboard (exactly to use as macros) but I hadn't discovered F13 to F22, thank you! That's exactly what I needed.
(Disclaimer, I'm the maintainer of this package, but this kind of use is exactly why I created it at the beginning)
If you know how to use HTML+CSS and would like to generate full-fledged cards, you could use a package such as html2image [0] to combine the text, the image and a card-template image into one final image.
Chrome/Chromium has to be available on Colab Notebooks though, that's the only requirement.
Using basic SVG without this package could also do the trick.
> Terms and Conditions, Price and Service List, Conditions.
> Dear customer,
> our price and service list, our terms and conditions, as well as further conditions which will come into effect on May 1, 2024, can be found on the USB stick.
Sheesh! Do you need a hug? Anyway, with chat GPT you can simply give it the image from the reddit post and get the OCRd and translated text. It's one step, it's fast, it's accurate enough. Why not use it?
That, and you can ask it to translate literally or colloquially, to summarize or explain about acronyms, cultural references, names, code, syntax, diagrams, graphics, or anything else.
GP: If you're going to play a curmudgeon, at least get some first hand experience with what you choose to complain about, otherwise your curmudgeoning isn't very effective, and you complain about things that aren't actually problems, and miss out on complaining about real problems.
I love to hate and complain about Unix and X-Windows and C++ and GCS, but that's because I've used them, not because I succeeded in avoiding them.
Prompt: Write an a cappella cover of a Philip Glass song in Simlish.
ChatGPT-4:
Creating an a cappella cover of a Philip Glass song in Simlish presents an interesting challenge. Philip Glass is known for his minimalist compositions that often consist of repetitive structures, and Simlish is a nonsensical language. Since Glass's compositions are largely instrumental, I will create an a cappella adaptation inspired by his musical style while using Simlish-like sounds.
Verse 1:
Doo doo zib, doo doo zib, doo doo zib, doo doo zib,
Bada bada zoob, bada bada zoob, bada bada zoob, bada bada zoob,
Glarbni glarbni glarb, glarbni glarbni glarb, glarbni glarbni glarb, glarbni glarbni glarb,
Sul sul sul, sul sul sul, sul sul sul, sul sul sul.
Chorus:
Froodle froodle, zibba zibba,
Dag dag, drib drib, yibbs yibbs,
Slooble slooble, wib wib, dor dor,
Lerpna lerpna, gort gort, zor zor.
Verse 2:
Doo doo zib, doo doo zib, doo doo zib, doo doo zib,
Bada bada zoob, bada bada zoob, bada bada zoob, bada bada zoob,
Glarbni glarbni glarb, glarbni glarbni glarb, glarbni glarbni glarb, glarbni glarbni glarb,
Sul sul sul, sul sul sul, sul sul sul, sul sul sul.
Chorus:
Froodle froodle, zibba zibba,
Dag dag, drib drib, yibbs yibbs,
Slooble slooble, wib wib, dor dor,
Lerpna lerpna, gort gort, zor zor.
Remember, this adaptation is meant to be playful and fun, as it doesn't have any real meaning or convey any specific message. The focus here is on capturing the essence of Philip Glass's minimalist compositions using Simlish-like sounds in an a cappella context.
I wrote a Python package [1] that does something similar! It allows the generation of images from HTML+CSS strings or files (or even other files like SVGs) and could probably handle PDF generation too.
It uses the headless version of Chrome/Chromium or Edge behind the scenes.
Writing this package made me realize that even big projects (such as Chromium) sometimes have features that just don't work. Edge headless wouldn't let you take screenshots up until recently, and I still encountered issues with Firefox last time I tried to add support for it in the package. I also stumbled upon weird behaviors of Chrome CDP when trying to implement an alternative to using the headless mode, and these issues eventually fixed themselves after some Chrome updates.
Yeah it's the same concept, instead of .screenshot you do .pdf in pupetteer.
But with pdfs the money is on getting those headers and footers consistent and on every page, so you do need some handcrafted html and print styling for that (hint: the answer is tables).
For further nitpicking: "etc." shall also end with '.' as it is the abbreviated form of "et cetera/caetera". Also, when used in an enumeration, it shall be preceded by a comma.
It is, at least, fairly well accepted as a thing. Name a "fact" that has been accepted as a learning, dive into it, find that it hasn't held up. :(
Some are purely on the popular science side of failure. The 10k of practice was basically thrown out, but the original research still seems good. They never claimed "if you do 10k of work, you will be good."
The "marshmallow test," though, seems completely tossed? Maybe there was something there?
Anchoring and other items? Not sure how well those have survived. :(
- Stanford Prison Experiment; Not an experiment, abuse was scripted, experimenter constantly intervened, reactions of participants were faked, and there was not even a scientific hypothesis they were testing. Definitely read the paper[0] debunking it.
- Milgram Experiment: (the one where people were ordered to shock actors) No good evidence for it. Researchers did not follow script, implausible levels of agreement between different experiments. Killer line is, “only half of the people who undertook the experiment fully believed it was real and of those, 66% disobeyed the experimenter.”
- Robber's Cave: (the one where two groups of kids immediately formed tribal hatred between one another) The conflict was orchestrated by experimenters and the experiment was actually repeated because the first time the kids absolutely refused to turn on one another. More information at [1].
- At best, weak evidence for implicit bias testing and stereotype threat.
- Weak evidence of "facial feedback" (smiling causes a good mood and frowning causes a bad mood)
- Good evidence against "ego depletion" (the idea that willpower is limited in a muscle-like fashion)
- Mixed evidence for Dunning-Kruger effect
- Questionable evidence for "hungry judge" effect (the idea that judicial sentences are massively more merciful in the morning and after a lunch recess due to "ego depletion" - this is also thoroughly debunked here [2])
- The 10,000 hours of practice leading to expertise idea has been disowned by its proponents
- No good evidence that tailoring teaching to students’ preferred learning styles has any effect on objective measures of attainment.
- No good evidence that brains contain one mind per hemisphere. i.e. the left-brain, right-brain split that people talk about, especially after the link between the hemispheres is severed.
- No good evidence for left/right hemisphere dominance correlating with personality differences.
- Most people talking about Dunning-Kruger have no idea what it actually means. The actual purported bias is much weaker than people claim - basically, that everyone either overestimates their ability, but that estimation is still positively correlated with actual ability, or estimated ability has basically no correlation with actual ability and everyone is just guessing.
- Increasing your wealth does in fact make you happier at a predictable rate. There is no "plateau" of wealth or income - what appears to be a plateau is misleading displays of data. In effect, increasing income by a proportional rate will increase reported happiness by a fixed rate. For example, say you make $10, and your happiness is 50. Then, your income increases to $20 and your happiness increases to 60. Then, doubling your happiness is necessary to increase your happiness by 10. It's a logarithmic function; plotted on a standard axis, it looks like a plateau, but plotted on a logarithmic scale and it's a constantly increasing line.
- Hedonic Adaptation (aka the hedonic treadmill) is a myth. Bad life events (divorce, disability, death of a loved one) all have negative long-term effects on happiness. Vice versa for positive events.
The french example sounds off in my opinion, it seems to mix up its consonants/ vowels.
The "OU" sound from "nous" sounds like "EU", or like if the sound was skipped.
The "OH" sound from "sommes" sounds like "EU" (again, but less pronounced).
The "T" sound from "trop" becames "P" ("pro").
