It's not like a simple embedding search takes that much longer to implement. Especially on short descriptions where you don't have to deal with chunking. And if you let an LLM write the code it's even less of a difference. Combine that with embedding search promising to solve all your search problems, and I understand why people often skip over full text search and go straight to embeddings
Even that is an oversimplification unless you are doing something very basic.
Volume of documents, size of documents, versioning, frequency of update, documents similar or overlapping information, how much or exactly what you need for the LLM to understand, AI friendly documents, who has access and at what level, blue teaming, red teaming, multi-lingual, does the LLM know the domain language of the user and documents.
I think Bitwarden implemented some vector search in their password search feature ... totally annoying it gives me back all kinds of stuff that I don't care.
I want fuzzy search like 95% of time and then I might consider having additional list of things that can be suggested by vector search.
Bandcamp has had legendarily bad semantic search for as long as they've been around. It's often completely impossible to find an artist or album or song even when you type the exact name.
ahh now I realize why I get so much completely irrelevant search results in many sites recently. I mean I'm searching for betel and you're giving me nuts. haha
A good UI could do these and also exact match, give some point system to the results, then order them and perhaps use a bold highlight to reflect what parts of the input query reflected in each result.
Bitwarden has lost the plot. The most recent Windows update is so bad. It has way lower information density in the UI, more buttons to click for the same use, no longer puts focus on the search field by default (this one makes me irrationally angry), and on one of my Win 11 installs can't lock the vault, manually or automatically. How could they mess up such a simple app that worked fine for so long?! What perverse incentives caused this nonsense?!
Yeah I cant imagine my job without it anymore, in my hobby projects I dont really use it because its more about learning new stuff but for work I dont really care
That's so depressing, and a real loss for your employer. Even if they neither know nor care that you are now sandbagging them, you still are. You aren't making real gains because you're tossing out value of equivalent or greater worth (your learning and engagement)
Most places I worked at cared very little for quality code, there was much more pressure on shipping fast even if it meant incurring technical debt, crap performance for end users, or developers leaving due to legacy code accumulation that nobody understood anymore.
I'm glad there is a tool that let's these companies have even shittier code shipped even faster. The faster they burn down the better.
You can only learn and engage so much in a day. In my head, it can be healthy to shift from tiring yourself out via work to tiring yourself out at home. You're not sandbagging them, you're setting boundaries on how much you're willing to do. If this is a problem for the employer, they can act accordingly.
I'm amazed you think typical corporations care about staff learning and engagement in the first place.
There's a reason they're trying to replace humans with AI: they just want outcomes. People learning and growing is only useful if it generates better outcomes. If you can get the same thing with a bunch of reverse centaurs, from a corporate perspective that's better: labour becomes more fungible and you can spend even less on training and investment in staff (assuming you ever did). And do it right and those folks will just train your machines to make them even better (see: Meta capturing worker activity and reallocating large numbers of staff to data labelling).
Sure, but that's a big big big big big big big big big big "if".
All AI has really succeeding in proving so far is that humans CAN really, very much "keep up", despite repeated repeated repeated repeated assertions that in six months it will not be so
Oh I'm aware. I'm not saying it makes any g-d sense. I'm just saying that's the corporate logic. So for those of us stuck in AI pilled orgs, the best bet is to play the game and keep your skills sharp on the side in case the whole thing goes pear shaped.
But it isn't a loss for any employers. They're not being sandbagged in any way. It's the path they've chosen, knowingly and willingly.
I'm with you except that the economy will crash when it turns out everyone stopped creating real value. ...and in the mean time every real product I have to use is getting worse.
Where they created value wasn't just the CRUD app but developing their skills, supporting communities that asked and answered questions to build public knowledgebases. They adapted to painfully repetitive tasks by developing tools that made expressing common ideas simple. In losing the pain of repetition, we lost the incentive towards abstraction. The forces in opposite directions cancelled out, creating growth for AI companies but overall stagnation due to the immense amount of value lost because before AI there was never a dollar value put on it.
Its fun but is it really effective ? I mean I checked the LLM one and I came out more confused about a topic I already know about, I find the best way to to learn using LLMs is to just generate an example try to somewhat get a mental model of how it works and then ground my understanding with traditional documentation and resources, its an iteration of a technique I used to do in college where I would read the textbook questions first to understand what is important and then read the chapter
I assume different ways of learning work for different people. For me personally, it's taking a piece of paper and drawing the diagram of how things work together; of if it's some math, then, again, using the pen and paper to follow the text. I can very much accept that for some people playing the simulation is a good way to touch the new problem space. I can easily imagine that for some topics, let's say, traffic signal automation, a careful simulation game will probably give more information than reading papers or manuals.
Game-based learning, described by Comenius, works if someone else prepares “a game” for you. E.g. like a dungeon master. :)
Otherwise you probably get more confused as you have mentioned.
On the other side, Peter Diamandis describes a situation where a bunch of kids were given a internet-connected computer and they had no teacher. Instead of it there was a “grandma” that checked kids from time to time.
After that there was a knowledge test that revealed “no teacher” approach was more efficient.
This doesn't make sense, I enjoy making bread at home but it costs 10x and tastes like dog shit I dont want to spend my time perfecting the craft of making bread for my daily needs (maybe once in a while its a soothing activity), I want someone smarter than me to spend his entire life coming up and perfecting a solution and exerting more time and effort than I can afford and I am very happy to support him so I can stop worrying about it and focus on what I want to do
Makes perfect sense to anyone good at using these models. What doesn't make sense is that analogy. Typing prompts isn't even close to as difficult to baking bread.
> Typing prompts isn't even close to as difficult to baking bread
Depending on how good you are at this task. If typing prompts was that easy, there won't be so many tutorials, blog posts, and framework (Act as ... etc)
But there is a difference though. You can ask LLM for "how to write a prompt for ... to prompt you". You can't do that with bread.
>Makes perfect sense to anyone good at using these models.
It doesn't really, because whenever I ask them what did they actually create, its always a shitty dashboard or a finance tracker or something derivative and worse than what is out there
You're missing the point that it isn't worse than what's already out there for them.
They've implemented only the parts they need, and removed all the crap that just complicates the system for them. They've made it do exactly what they need, exactly how they need it. It's something that you couldn't afford to do previously, sometimes even as a programmer. Now, it's often quick and easy, up to a certain complexity.
> They've made it do exactly what they need, exactly how they need it.
…until it breaks, or the bot goes off and does something ridiculous that you can’t understand without domain expertise. Which always happens.
I’m sympathetic to your argument, but I also strongly believe that most of these so-called “exactly what I need” projects will be abandoned within a fairly short time. That’s totally fine, but it’s not where most of the effort in professional software lies.
> I enjoy making bread at home but it costs 10x and tastes like dog shit
I am sorry but you are holding it wrong. Among all the things you can do yourself cgeaper and better, bread is probably the further most low hanging fruit.
How exactly do you envision this ? you will ask the ai to make youtube but better, people seperate the "what" from the "how" but they have a very complex relationship
Have you tried most powerful recent models? You may even don't understand at all "how" - what you get is end result you asked for, verified and tested. I am pretty sure if I can vibe code quite non trivial solution in just say 4-8 hours today, then why will it be impossible say in a year or two to vibe code something at the level of most sophisticated apps and services today? Pretty reasonable expectation taking into account what was possible just a year ago and what you can make today without even understanding "how".
> then why will it be impossible say in a year or two to vibe code something at the level of most sophisticated apps and services today?
Replace "vibe coding" with "outsource to India" and it's the same situation we were in 20 years ago: I remember around the time when YouTube had well-established itself (2009-ish?) and so a cottage-industry mushroomed all selling visual-lookalike YouTube clones, but implemented as monolithic single PHP project or WordPress plugin, using the local filesystem for video file storage (or worse: Base64-encoded text in MySQL, lovely).
...to someone with no prior experience or knowledge how highly-scalable, Google-tier web applications (like the real YouTube) work or are built, these "Me-Too-Tube" sites were indistinguishable from the real thing and as far as they were concerned they were happy with it.
Never mind that even if those $25 scripted websites were ever actually scalable, it isn't enough to simply have a video-sharing site; you need to get millions of people to decide to start using it - and that's something which will elude Claude's abilities... possibly forever, I feel.
I feel like the actual core mechanic at improving is the actual act of "recall", it doesnt matter what you do if its a form of recall it is effective and very awkward in practice because you just sit there waiting for your brain to do a mysterious thing
reply