581–590 of 615 posts
Earlier quoted context omitted.
Outside of big tech, those titles aren’t common. Level X SWE vs staff vs principal doesn’t mean anything to a lot of people who aren’t in that orbit.
Yes when I started working, "staff" meant entry-level. My first job out of school was a "staff consultant." So I'm always tripped up when I see "staff" used to mean "very senior/experienced"
About "people still thinking LLMs are quite useless", I still believe that the problem is that most people are exposed to ChatGPT 4o that at this point for my use case (programming / design partner) is basically a useless toy. And I guess that in tech many folks try LLMs for the same use cases. Try Claude Sonnet 3.5 (not Haiku!) and tell me if, while still flawed, is not helpful. But there is more: a key thing with L…
Earlier quoted context omitted.
The "world model" of an LLM is just the set of [deep] predictive patterns that it was induced to learn during training. There is no magic here - the model is just trying to learn how to auto-regressively predict training set continuations. Of course the humans who created the training set samples didn't create them auto-regressively - the training set samples are artifacts reflecting an external world, and knowledge…
>Whether these training set predictive patterns result in the model performing as you might hope on an unseen text depends on the similarity of that text to samples in the training set. >similarity yes, except the computer can easily 'see' in more than 3 dimensions with more capability to spot similarities, and can follow lines of prediction (similar to chess) far more than any group of humans can. that super-human a…
The intelligence we see in LLMs is to be expected - we're looking in the mirror. They are trained to copy humans, so it's just our own thought patterns and reasoning being output. The LLM is just a "selective mirror" deciding what to output for any given input.
Earlier quoted context omitted.
> Good communication with LLMs is the least keywords used to make it deducible for LLM what you exactly want. I am not sure that is the case, at least with a large number of LLMs. CO-STAR and TIDD-EC are much about structure and explanation than brevity.
Finding what works for an llm and what not is also part of communication skills. Though I do not have a good idea what is _bad_ communication with an llm. People say that sometimes, but when specific examples arise I do not see really anything more than limitations of llms (and the improvements they often suggest do not do anything either). So it would be good to have some more concrete examples, unless that is about…
Bad communication: "My webapp doesn't work"
Good communication: "Nextjs, [pasted error]"
Bad communication is giving irrelevant information, or being too ambiguous, not providing enough or correct detail.
Then another example of good communication and efficiency in my view is for example "ts, fn leftpad, no text, code only".
I myself can understand what it means when someone was to prompt it and LLM can understand such query for all domains.
Although if I was using Copilot I would just write the bare minimum to trigger the auto complete I want so
const leftPad =
is probably enough.
Earlier quoted context omitted.
>Whether these training set predictive patterns result in the model performing as you might hope on an unseen text depends on the similarity of that text to samples in the training set. >similarity yes, except the computer can easily 'see' in more than 3 dimensions with more capability to spot similarities, and can follow lines of prediction (similar to chess) far more than any group of humans can. that super-human a…
The inner workings/representations of transformers/LLMs aren't a total black box - there's a lot of work being done (and published) on "mechanistic interpretability", especially by Anthropic. The intelligence we see in LLMs is to be expected - we're looking in the mirror. They are trained to copy humans, so it's just our own thought patterns and reasoning being output. The LLM is just a "selective mirror" deciding wh…
Earlier quoted context omitted.
The environmental arguments are hilarious to me as a diehard crypto guy. The ultimate answer to “waste” of electricity arguments is that energy is a free market and people pay the price if it’s useful for them. As long as the activity isn’t illegal then training LLMs or mining bitcoins, it doesn’t matter. I pay for the electricity I use.
One argument against that line of thinking is that energy production has negative externalities. If you use a lot of electricity, its price goes up, which incentivizes more electricity production, which generates more negative externalities. It will also raise the costs for other consumers of electricity. Now that alone is not yet an argument against crypto currencies, and one person's frivolous squandering of resour…
Acknowledging that facilitating scams (eg pig butchering) are cryptocurrency's primary (sole?) use case, I'm willing to look the other way if we end up with the grid we need to address climate crisis.
Earlier quoted context omitted.
It would be out of date in months. Things that didn’t work 6 months ago do now. Things that don’t work now, who knows…
Do you mean performance that was missing in the past is now routinely achieved? Or do you actually mean that the same routines and data that didn't work before suddenly work?
Each new model opens up new possibilities for my work. In a year it's gone from sort of useful but I'd rather write a script, to "gets me 90% of the way there with zero shots and 95% with few-shot"
Earlier quoted context omitted.
Quick example. I was implementing dot product between two quantized vectors that have two different min/max quantization ranges (later I changed the implementation to just centered range quantization, thanks to Claude and what I'm writing in this comment). I wanted to still have the math with the integers and adjust for the ranges at the end. Claude was able to mathematically scompose the operations as multiplication…
LLMs being able to detect bugs in my own code is absolutely mind blowing to me. These things are “just” predicting the next token, but somehow are able to take in code that has never been written before and somehow understand it and find what’s wrong with it. I think I’m more amazed by them because I know how they work. They shouldn’t be able to do this, but the fact that they can is absolutely jaw dropping science f…
Sure if you look at new project x then in totality it's a semi unique combination of code, but breaking it down into chunks that involve a couple lines, or a very specific context then it's all been done before.
In spite of all this progress, I can't find LLMs that solve simple tasks like: Here is my resume. Make it look nice (some design hints). They can spit html and css, but not Google doc. On the other hand, Google results are dominated by SEO spam. You can probably find one usable result on page 10. The problem is not technology. It's a business model that can support the humans feeding data into the LLM.
> They can spit html and css, but not Google doc. Wow. At this stage, I think people are just searching for excuses to complain about anything that the LLM does NOT do.
If a multi-modal LLM can read a 100 page PDF and answer questions about it or replace a median white collar worker, this should be a relatively trivial task. Suggest some nice fonts, backgrounds and give me something that I can lightly edit and generate a PDF from.
In spite of all this progress, I can't find LLMs that solve simple tasks like: Here is my resume. Make it look nice (some design hints). They can spit html and css, but not Google doc. On the other hand, Google results are dominated by SEO spam. You can probably find one usable result on page 10. The problem is not technology. It's a business model that can support the humans feeding data into the LLM.
Why would they be able to output a Google doc? It's a proprietary format. The closest thing would be rich text format to copy paste.
Google doc + PDF is likely the most commonly used combination based on what I see in the SEO spam.
Some of them make you watch ads and then allow you to download something that looks like a doc, but you'll find out soon that you downloaded a ppt with an image that you can't edit.