This means that the results (both of the task and of the learning by the student) are lower if the student uses an LLM first, but slightly improves if they use it second
Exactly what I thought of reading this, that chapter is genuinely one of the most affecting things I've ever read. The horror of it keeps growing as he continues to describe awful manual task after the other.
I've found good results from summarizing my documents using a large context model then embedding those summaries using a standard embedding model (e.g. e5)
This way I can tune what aspects of the doc I want to focus retrieval on, it's easier to determine when there are any data quality issues that need to be fixed, and the summaries have turned out to be useful for other use cases in the company.
I was trying to do this recently for Web page summarization. As said below the token sizes would end up over the context length, so I trimmed the html to fit just to see what would happen.
I found that the LLM was able to extract information, but it very commonly would start trying to continue the html blocks that had been left open in the trimmed input. Presumably this is due to instruction tuning on coding tasks
I'd love to figure out a way to do it though, it seems to me that there's a bunch of rich description of the website in the html
Can second Statistical Rethinking though if you have the basics of stats and want to learn it again from a very different, more causal/bayesian point of view.
The book Lynchpin talks about this and calls it "the resistance", the feeling of avoidance you get when nearing shipping something or even to sitting down and starting an ambitious project.
I've found it useful to have a name for it so I can recognize when I'm falling prey to "the resistance" and get myself to stop procrastinating or to "just ship it".
Right I was confused when the article mentions the other parameters other than the moon and sun ones track other astronomical variables, surely they are modeling geological and hydrological variables also (or potentially primarily)
Slack groups have filled in the meetup space in my life, mlops.community and locally optimistic are two of the best for what it sounds like you're looking for
One downside for milvus is that version 1 doesn't do filtering (necessary for most search applications) and version 2 is significantly slower.
Google's vector nearest neighbors offering, weaviate, and Vespa are much better options if you're expecting to extend to more realistic workloads
From an accessibility perspective it's a disaster too. My granny is visually impaired, but loves watching tv. She's been able to get by for decades by memorizing the commands needed to get where she wants to go (she had a list of nintendo cheat code-like instructions on how to get to various channels she wanted on the satellite e.g. down-down-left-left-enter gets her to her show)
We tried to get her into Netflix, but the menus change far too often for this strategy to be of any use. Of course you can use the screen reader/narrator, but you can imagine how frustrating it is trying to find the carousel you're looking for by waiting for the screen reader to tell you, it's frustrating enough doing it visually!!
Interestingly Leitrim and other counties in the north west he mentions have been high on the list of places people have escaped to from Dublin during the pandemic. Many people are now living there and working remotely for Dublin companies, and there are far too _few_ houses there now, and house prices have skyrocketed
This was a real jolt to read though. I've been really bullish about WFH or hybrid work for the future, since as an IC I've seen nothing but the benefits as you mention. I never thought of the stress of remote work in a management role though, so thanks for sharing!
Could you elaborate on why you think low energy deep learning was a misguided promise for SNNs? Just came across them for the first time last week and the low energy promise seemed like their most interesting aspect!
I was in the same boat until I had a baby who was a _terrible_ sleeper during the night. Once I was down to 4-5 hours sleep a night, napping during the day was heaven!
Sometimes I'd have had too much coffee or been overstimulated through work or something, I found [these tips from the military](https://www.inc.com/jessica-stillman/the-trick-soldiers-use-...) really helpful. Even now, I pretty much only need to relax my jaw and do a few rounds of 4-7-8 breathing and I can have a nap on demand!
I had done that, but my ssh completions weren't working great at all. I've installed ohmyzsh as recommended below and it's great, definitely a step up from bash.
What was the reason for them doing this do you know? From my experience with it over the last year, zsh is slightly worse at autocomplete than bash, with no advantages.
Is there something I'm missing, like a good default .zshrc?
Interestingly he recently discussed how using LLMs tends to remove this desirable difficulty: https://davidepstein.substack.com/p/a-risk-of-cognitive-conv...
This means that the results (both of the task and of the learning by the student) are lower if the student uses an LLM first, but slightly improves if they use it second