What a great read! You got me at the base64 oddity. I also stumbled over this, while trying to dodge some LLM limitation. (was trying to generate images in a time before multimodal was a thing. it only worked to a…
Naaa, you have to think of the poster in options. Like, "would you want to have some extra publicity with your poster for an extra 100 bucks?"
I never realized; thanks for pointing that out. Sneakers is one of my favorite movies.
A while back, someone made https://meet.hn. It's a map where people from hackernews could locate themselves. Of course this is by far not comprehensive, but it gives you an idea of where the people are from.
Exactly my point of view. For the most part I do not root for my preferred technology, but rather try to inform my powers about the caveats I see. This way at least the right aspects to check have a chance to enter the…
Yes, they can. Meta described a clever way in their paper on training Llama3 [1] (in section about factuality). The idea is to sample several answers to a question that you know the answer to. Let an LLM decide if the…
We have a couple of systems at work that incorporate LLMs. There are a bunch of RAG chatbots for large documentation collections and a bunch of extract-info-from-email bots. I would none of these call an agent. The one…
Came here for exactly that. Thank you.
Bolzman machines were there in the very early days of deep learning. It was a clever hack to train deep nets layer wise and work with limited ressources. Each layer was trained similar to the encoder part of an…
This comment caught me off guard! I literally blew my coffee all over the table.
I second that thought. There is a pretty well cited paper from the late eighties called "Multilayer Feedforward Networks are Universal Approximators". It shows that a feedforward network with a single hidden layer…
Motorola used to have a one bit microprocessor, the MC14500B.
I simply love this book!
At the very beginning of my journey I did some fine tuning with Lora on a (I believe) Falcon model, but I haven't looked at it since. My impression was that injecting knowledge via fine tuning doesn't work, but tweaking…
I have not encountered this problem yet. When I was talking about the format of the answer I meant the following: No matter if you're using Langchain, Llamaindex, something self made, or Instructor (just to get a json…
I also think of the retrieval part as a bottleneck and I am super excited of what the future holds. In particular, I wonder if RAG systems will soon be a thing of the past, because end to end trained gigantic networks…
That is an interesting observation. I have not gotten to the point of too long cycles and I can think of two reasons for that. Maybe my use case is narrow enough, so that in combination with a rather constraining and…
The company I work for has tons of documentation and regulations for several areas. In some areas the documents are well over a thousand and for the ease of use of these documents we build RAG based chat bots. This is…
I have been to a couple of hackathons as participant and as organizer. Some sessions where really good and some were really terrible. The biggest takeaway for me in organizing a hackathon is to keep in mind that…
I read it the same way as you did, or at least it's an approximation. In general that's not really surprising. I remember discussions from some years ago about larger networks leading to smother loss surfaces.
There is also the evo64 project which rebuild the c64 with modern parts.
I love this thread. The question is so unspecific that it's like a version of "To get the right answer you need to post something wrong on the internet".
I think that the display is not used at all. If I understood correctly, the scart connector is hosting a hidden uart interface. This let's you connect a serial terminal via three cables. (You can e.g. buy a serial to…
I use monokai and dracula, depending on the environment. If i can alter something, I usually go for dracula and FiraScript as font.
I really love this book. Beautiful data and beautiful visualizations are also nice reads, but beautiful code has a special place in my heart.
What a great read! You got me at the base64 oddity. I also stumbled over this, while trying to dodge some LLM limitation. (was trying to generate images in a time before multimodal was a thing. it only worked to a…
Naaa, you have to think of the poster in options. Like, "would you want to have some extra publicity with your poster for an extra 100 bucks?"
I never realized; thanks for pointing that out. Sneakers is one of my favorite movies.
A while back, someone made https://meet.hn. It's a map where people from hackernews could locate themselves. Of course this is by far not comprehensive, but it gives you an idea of where the people are from.
Exactly my point of view. For the most part I do not root for my preferred technology, but rather try to inform my powers about the caveats I see. This way at least the right aspects to check have a chance to enter the…
Yes, they can. Meta described a clever way in their paper on training Llama3 [1] (in section about factuality). The idea is to sample several answers to a question that you know the answer to. Let an LLM decide if the…
We have a couple of systems at work that incorporate LLMs. There are a bunch of RAG chatbots for large documentation collections and a bunch of extract-info-from-email bots. I would none of these call an agent. The one…
Came here for exactly that. Thank you.
Bolzman machines were there in the very early days of deep learning. It was a clever hack to train deep nets layer wise and work with limited ressources. Each layer was trained similar to the encoder part of an…
This comment caught me off guard! I literally blew my coffee all over the table.
I second that thought. There is a pretty well cited paper from the late eighties called "Multilayer Feedforward Networks are Universal Approximators". It shows that a feedforward network with a single hidden layer…
Motorola used to have a one bit microprocessor, the MC14500B.
I simply love this book!
At the very beginning of my journey I did some fine tuning with Lora on a (I believe) Falcon model, but I haven't looked at it since. My impression was that injecting knowledge via fine tuning doesn't work, but tweaking…
I have not encountered this problem yet. When I was talking about the format of the answer I meant the following: No matter if you're using Langchain, Llamaindex, something self made, or Instructor (just to get a json…
I also think of the retrieval part as a bottleneck and I am super excited of what the future holds. In particular, I wonder if RAG systems will soon be a thing of the past, because end to end trained gigantic networks…
That is an interesting observation. I have not gotten to the point of too long cycles and I can think of two reasons for that. Maybe my use case is narrow enough, so that in combination with a rather constraining and…
The company I work for has tons of documentation and regulations for several areas. In some areas the documents are well over a thousand and for the ease of use of these documents we build RAG based chat bots. This is…
I have been to a couple of hackathons as participant and as organizer. Some sessions where really good and some were really terrible. The biggest takeaway for me in organizing a hackathon is to keep in mind that…
I read it the same way as you did, or at least it's an approximation. In general that's not really surprising. I remember discussions from some years ago about larger networks leading to smother loss surfaces.
There is also the evo64 project which rebuild the c64 with modern parts.
I love this thread. The question is so unspecific that it's like a version of "To get the right answer you need to post something wrong on the internet".
I think that the display is not used at all. If I understood correctly, the scart connector is hosting a hidden uart interface. This let's you connect a serial terminal via three cables. (You can e.g. buy a serial to…
I use monokai and dracula, depending on the environment. If i can alter something, I usually go for dracula and FiraScript as font.
I really love this book. Beautiful data and beautiful visualizations are also nice reads, but beautiful code has a special place in my heart.