Alternatives
Products that do what NanoEuler – GPT-2 scale model in pure C/CUDA from scratch does
Hi everyone, I started working on nanoeuler after the ban of anthropic's fable because my ambition and dream is to work in the AI field in anthropic. The two interesting reasons that led me to create nanoeuler were the first, interfacing with llm does not mean understanding how they are composed and two, working on llm with a very low-level layer to understand the correlation between parameters and data and growth of the model and how the GPU works and how some layers can be optimized. So I started working on it with a research aspect by making nanoeuler grow more and more but doing one step…
- 1NG
Hi everyone, I started working on nanoeuler after the ban of anthropic's fable because my ambition and dream is to work in the AI field in anthropic. The two interesting reasons that led me to create nanoeuler were (1) interfacing with llm does not mean understanding how they are composed and (2), working on llm with a very low-level layer to understand the correlation between parameters and data and growth of the model and how the GPU works and how some layers can be optimized. So I started working on it with a research aspect by making nanoeuler grow more and more but doing one step after…
Jun 2026 · github.com
- 2GG
A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me. But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility. I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context.…
Jul 2026 · github.com
- 3
- 4
- 5
- 6
- 7AO
Hey hackers, the world needs more AI researchers with good taste, and hardcore software folks have some of the best. Many software friends mentioned they learn better from implementations than from papers, but existing open-source examples rarely go beyond basic nanoGPT-level demos. To help bridge that gap, I spent the last two months full-time reimplementing and open-sourcing a self-contained implementation of every major modern deep learning technique from scratch. The result is beyond-nanoGPT, containing 20k+ lines of handcrafted, minimal, and extensively annotated PyTorch code. I'd love…
2025 · github.com
- 8SW
Chrome now includes a native on-device LLM (Gemini Nano) starting in version 138. I've been building with it since it was in origin trials, it's powerful but the official Prompt API is still a bit awkward: - Enforces sessions even for basic usage - Requires user-triggered downloads - Lacks type safety or structured error handling So I open-sourced a small TypeScript wrapper I originally built for other projects to smooth over the rough edges: github: https://github.com/kstonekuan/simple-chromium-ai npm: https://www.npmjs.com/package/simple-chromium-ai…
2025 · github.com
- 9OS
Everyone saw the AlphaEvolve hype. I got obsessed with how it might work under the hood and decided to just build it myself. My setup uses GPT-4.1 to mutate matrix multiplication code, guided by a bunch of hand-crafted mutation strategies (loop reordering, tiling, Strassen, etc.). Each candidate is evaluated on both speed and accuracy. Then I apply Pareto selection with crowding distance to evolve better ones over generations. I ran into all the usual LLM reward hacks-returning the input, calling np.dot, etc. So I forced primitive-only implementations and tightly constrained the mutation…
2025
- 10RA
Hi there, looking for feedback on my new project "Featherless.AI" The idea is to allow users to run all the models on hugging face instantly. Via the OpenAI API compatible endpoint. Why? Because its a real chore to download models and spin up GPUs, especially if you want to test multiple models. Not to mention GPUs cost multiple dollars an hour to rent. And if we want more people to use open source AI, we got to make it easier for them to try and play with all of them. So what if instead of spinning up dedicated GPUs per model (which is what every provider is doing) We can startup a LLM…
2024 · featherless.ai
- 115L
We've built InferX, a specialized runtime environment that fundamentally changes how LLMs are served. The core problem we solve is the latency bottleneck in AI inference, especially with large models. Current systems waste resources or suffer from painfully slow cold starts. InferX's AI-native architecture, with its "snapshot" technology, enables: * *Sub-2s cold starts:* Spin up models instantly. * *High density:* Serve more LLMs on the same GPUs. * *Optimal efficiency:* Maximize GPU utilization. This isn't just another API; it's a new execution layer designed from the ground up for the…
2025 · github.com
- 12I3
I’ve been building an interactive 3D + 2D visualization of GPT-2. It displays real activations and attention scores extracted from GPT-2 Small (124M) during a forward pass. The goal is to make it easier to learn how LLMs work by showing what is happening inside the model. The 3D part is built with Three.js, and the 2D part is built with plain HTML/CSS/JS. Would love to hear your thoughts or feedback!
Mar 2026 · llm-visualized.com
- 13
- 14WB
Hey HN, After GPT-3 created waves in the tech industry, a lot of AI tools were emerging and with that, some AI website builders But the results seemed way too generic to us. It felt like the developers were rushing to catch the wave instead of building a proper tool We took our time, did months of RnD and finally came up with something better than what others in the market are doing. It’s got better design output. While it’s still in beta, I wanted to show HN what we did. Will appreciate the feedback when you guys try it out. Here is the link to signup for the beta:…
2024 · dorik.com
- 15IM
Hi guys, For my startup at www.mithrin.ai which is about create AI Chatbot Agents for websites, I wanted to create some free tools to attract traffic to the site and decided to create specialized chatbots powered by LLMs, similar to OpenAI's Custom GPTs. I realized that by using gpt-4o-mini, I could create quite powerful alternatives to GPTs that are free to the public for a very small cost (given how cheap the model api cost is). I've employed some throttling to prevent abuse and to avoid being charged too much. Then I integrated this with my main service and allowed users to use the…
2024 · mithrin.ai
- 16UD
Hi HN! I was inspired by Andrej Karpathy's llm.c (https://github.com/karpathy/llm.c), and wrote a full diffusion model training loop in CUDA. I learnt a lot about CUDA from Simon Boehm's Matmul blog (https://siboehm.com/articles/22/CUDA-MMM). Currently there is still a lot of room for optimization: the model is running at 45% speed of PyTorch with torch.compile. I'm curious about any thoughts or CUDA tips for convolutions.
2024 · github.com
- 17IU
This sounds clickbait, but it’s true: I used Claude Mythos to build the full site in 1 day. Then Anthropic removed the model, so I had to go back to Opus.
Jun 2026 · brandlm.ai
- 18S1
I wanted to build an inference provider for proprietary AI models, but I did not have a huge GPU farm. I started experimenting with Serverless AI inference, but found out that coldstarts were huge. I went deep into the research and put together an engine that loads large models from SSD to VRAM up to ten times faster than alternatives. It works with vLLM, and transformers, and more coming soon. With this project you can hot-swap entire large models (32B) on demand. Its great for: Serverless AI Inference Robotics On Prem deployments Local Agents And Its open source. Let me know if anyone…
Nov 2025 · github.com
- 19HF
We have a massive GPU cluster and developed our own infrastructure to manage the cluster and train massive models. There's how it works: 1. You upload the dataset with preconfigured format into HuggingFaсe [1]. 2. Choose your LLM (e.g. LLaMa 70B, Mistral 7B) 3. Place your submission into the queue 4. Wait for it to get trained. 5. Then you get your trained model there on HuggingFace. Essentially, why would we want to do it? 1. We already have an experience with training big LLMs. 2. We could achieve near-perfect infrastructure performance for training. 3. Sometimes GPUs have just nothing to…
2023 · higgsfield.xyz
- 20NB
I've spent weeks curating technical implementation details of how companies are actually deploying LLMs and Generative AI in production. The database now contains over 300 case studies with detailed technical summaries (230,000+ words) focusing exclusively on architectural decisions, deployment patterns, and real engineering challenges. Key features: * Each case study is technically focused - no marketing fluff * 150+ entries from technical conference talks and panels (saving you 100+ hours of video watching) * Sophisticated filtering by technical stack, RAG implementations, monitoring…
2024 · zenml.io
- 21
Ultra-fast AI image generator powered by Nano Banana 2 Lite.
Jul 2026 · nanosceneai.com
- 22PA
Hi HN, I’m Thijs, new to the community and excited (and a bit nervous) to share what I’ve been working on: it's called Prototyper. The motivation: I was curious how much more "taste" you could get out of an LLM if you built the entire infra yourself: tool calling, code execution, rendering—instead of layering on top of existing stacks. Over the past year I built a custom compiler, runtime, and design engine from scratch to see if this could make LLM-driven design genuinely better. A few details: - Own compiler + code runtime → no shadcn, no third-party UI kit, no external execution layer. -…
2025 · getaprototype.com
- 23UC
Anthropic recently released a new model called Claude. As I was unable to access this model, I noticed a lot of discussions on Twitter regarding comparisons and use cases of Claude and ChatGPT. To keep track of these conversations, I created a repository that compiles information on the following topics: * Comparisons between Claude and ChatGPT * Use cases * Limitations of Claude Check it out and please create a bug/PR if more threads can be added: https://github.com/taranjeet/awesome-claude
2023
- 24
I find LLM interpretability extremely interesting and wanted to create a minimal repo for: - SAE training - Automatic feature interpretation - Visualizing features and running interventions through a GUI You can try it here: https://nanointerpret.pages.dev/ Or check the repo: https://github.com/Belluxx/nanointerpret
10d ago · nanointerpret.pages.dev
Ranked by how close each launch is in meaning, then by votes. Refine with a description →