Alternatives
Products that do what Wikipedia 10x, 100x Better does
Built substrate: https://github.com/bkrauth7/Planetary-substrate Protoytpe on GPT-4o. Stable + live. Nervous system interface. Proposing Wikipedia 10x, 100x better. Ben [email protected]
- 1
- 2
- 3
- 4WB
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
- 5
Exosquelette de biohacking et isolation à 700 épaisseurs
3d ago · ko-fi.com
- 6JN
We’ve been experimenting with how far a tiny model can go when it’s good at calling external tools - and have just released Jan-nano, a 4 B model trained for MCP. Jan-nano: - tops DeepSeek-V3-671B on MCP tool-use (SimpleQA 80.7%) - handles live web search and multi-step deep research - runs fully on-device (≈4GB VRAM) Tech notes - Base: Qwen3-4B - Fine-tuning: DAPO - We're going to release the full technical report soon Links - Demo tweet: https://x.com/menloresearch/status/1934809407604576559 - Model + GGUF:…
2025 · twitter.com
- 7IE
Quick note on how it works and how I've done my batch embedding engine IgniteMS. The whole thing runs as one process using Rust, reading input, tokenizing, packing batches, keeping the queue full. TensorRT handles inference. Python is only as a wrapper. I built it this way because when you use more than couple of GPUs, the GPUs stop being the problem. CPU cannot feed them fast enough. One A100 can go through batches faster than Python can tokenize and feed, so the GPU just sits there idle waiting for work. Most of my time went into optimizing this. At 8 GPUs that was basically the entire…
Jun 2026 · github.com
- 8IW
Input a SMILES string (or pick one molecule from the examples) and it returns up to 100k molecules closest in 3-D shape or electrostatic similarity – from 10+ billion scale databases — typically in under 5-10 s. *Why it might interest HN* * Entire index lives on disk — no GPU at query-time, less than ~10 GB RAM total. * Built from scratch (no FAISS index / Milvus / Pinecone). * Index-build cost: one Nvidia T4 (~ 300USD) for one 5.5B database. * Open to anyone, predict ADMET, export results as CSV/SDF. Full write-up & benchmarks (DUD-E, LIT-PCBA, SVS) in the pre-print:…
2025 · cheese-new.deepmedchem.com
- 9VI
This was submitted before but it didn't seem to get much attention because I don't think the title was very descriptive and the submitter was brand new. I almost didn't click it but once I did I thought the project was pretty awesome and had a lot of promise. Hope this doesn't violate the rules, I have no horse in the game, but the creator is here on the site so hopefully he'll be able to answer your questions.
2022 · docs.vaxiin.io
- 10HT
Fun little project, had Gemini 2.5 Pro summarize HN's top 30 each hour, both the stories and comment sections. Pretty impressed with Gemini 2.5. It's probably the first model other than Claude 3.7 Sonnet where I actually find the output readable. I normally use 3.7 Sonnet for coding, but used Gemini for the codegen on this one as well. Was pretty impressed! Using Cursor, it seemed to instruction-follow better than Claude generally does, and remain lucid during very long agent sessions. Thanks for your feedback!
2025 · tinysums.ai
- 11AO
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
- 12IM
Hey HN! Thank you for all the support and feedback on my original submission 2 months ago. I've been improving the backend using a MCTS/AlphaZero approach and it's currently producing much better results. My long term goal is to allow users to manage multiple projects, deployed autonomously, both from scratch and by making continual updates all prompted with natural language. The cost of each project has been lowered to $9 as performance with smaller models has improved (I migrated from Claude-3-Opus to gemini-1.5-flash). Thanks for checking it out!
2024 · saas-quick.com
- 13BT
Hi everybody, this was my project to learn Zig and RISC-V+x86_64 assembly. Not sure if anybody is actually interested in yet another Brainfuck compiler, so I'll just write up some random things I learned while building it! - A primitive assembly stitching compiler is 10x faster than the interpreter. Did not expect that. - The generated x86 code is really bad (e.g. it always uses 6 or 7 byte sized instructions with 32-bit immediates when there are much smaller ones) but it doesn't really matter. Good code generated by GCC and clang for transpiled Brainfuck->C is not much faster as it's…
2025 · github.com
- 14NG
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…
Jun 2026 · github.com
- 15HC
Hello everyone, After recreating the accuracy/rough speed from David Page's implementation in hlb-CIFAR10 0.1.0 (18.1s on an A100, SXM4, Colab), it was down to some basic NVIDIA kernel profiling to figure out which operations were the long poles in the tent. Perhaps (somewhat?) unsurprisingly, the NCHW NHWC thrash was the worst part, but unfortunately the GhostBatchNorm was a barrier even using the faster-on-Ampere channels_last memory format. A quick note before continuing -- some may find the use of a convolutional network and on CIFAR10 to be curious. A quick answer to that would be…
2023 · github.com
- 16E0
2023 · earthly.dev
- 17
Hi everyone, Please checkout compute.cx which is a simple cli interface for using on demand GPUs from RunPod and HotAisle. I created this because I really like the ease of modal.com for severless gpu access, but don’t always want to pay their markup. Compute.cx gives the same DX but on public on-demand GPUs like runpod and hotaisie. Please try it out, and write to me [email protected] for any questions/suggestions, or file a bug report on https://github.com/theoriclabs/docs.compute.cx Thanks! Harsh Gupta https://x.com/hargup13 P.S. BYOK AWS, GCP and…
17d ago · compute.cx
- 18WA
Witchcraft is from-scratch Rust reimplementation of Stanford's XTR-Warp (SIGIR'25, https://arxiv.org/abs/2501.17788 ) multi-vector semantic search engine. Witchcraft runs out of a single SQLite database, is blazing-fast (21ms p.95 end-to-end search latency on NFCorpus on a MacBook Pro), accurate (33% NDCG@10), and easy to deploy in your own apps. The Witchcraft repo also comes with Pickbrain, a sample app and agent skill that you can use to instantly query across all your Claude Code and Codex CLI sessions, effectively giving your agents global long-term memory. Please…
Apr 2026 · github.com
- 19TS
We have built Tarit as a hypervisor built from ground up for running AI agent and RL environments. It is based on rust-vmm and can be used as a replacement for firecracker. Firecracker was built to serve a different need of primarily serverless compute and hence does not have primitives like live snapshots without pausing the VM operations. We also provide a basic orchestrator that handles placement of the microVMs, creating clusters with HA, maintaining a warm pool of VMs, and takes care of setting up networking and monitoring. Our benchmarks on a metal instance shows an acquire VM from…
Jul 2026 · github.com
- 20IM
Hey HN! I made a completely open sourced alternative to Weights and Biases with (insert cringe) blazingly fast performance (yes we use rust and clickhouse) Weights and Biases is super unperformant, their logger blocks user code... logging should not be blocking, yet they got away with it. We do the right thing by being non blocking. Would love any thoughts / feedbacks / roasts etc
2025 · github.com
- 21PT
Hi HN, I’ve been working the past year on something called Prototyper , and today we’re opening up the new version. The motivation is simple: whenever I built products in the past, I noticed the best ideas came after the “first version.” You try something, it feels wrong, you change it, repeat. Most tools make that painful. Prototyper is my attempt to make that loop natural—so you can explore ideas quickly instead of forcing them through a rigid workflow. This release includes: instant updates (no compile/refresh lag) simplified UI (months spent just removing steps) responsive by…
2025 · getaprototype.com
- 22
Hey yall, I built this for my makerspace. We wanted to let each other borrow things, but also didn't want to put up a big shiny sign saying "hey everyone, my garage has a super fancy oscilloscope just sitting there" and also didn't want to necessarily always need to say yes to everything. However, when I show it to people, they've been suggesting using it for other things like board games, or wedding equipment, etc. I'm still trying to find PMF, so please let me know what you think! For the stack, it's all Elixir + LiveView which is really nice, and then Fly.io, Fly's MPG, Tigris Data,…
25d ago · toolpool.garden
- 23SM
I am sharing a research-grade, open-source trading execution framework that achieves a median end-to-end decision latency of 890 nanoseconds on commodity hardware. The project is designed for education, systems research, and latency instrumentation, not for live trading. It focuses on understanding exactly where every nanosecond goes in a trading execution path. Key features: - Kernel-bypass networking: Direct userspace access to NICs via custom drivers, 20-50 ns RX latency - Lock-free SPSC/MPSC queues: Zero-copy architecture - SIMD feature extraction: About 40 ns per update using…
Dec 2025 · submicro.krishnabajpai.me
- 24MA
Hi HN! I've been working on Mesh, and I think it is time to it with you guys. Building on Cardano is difficult, because it lacks documentations and proper SDKs. This is where Mesh fills in this gap. With those beginner guides, is incredibly easy to get started, removing the pain of getting the simplest things to work. It is well engineered, the cloest "competitor" package size is over 10MB, while Mesh is less than 300KB, thus its light weight and your dApp will run fast. It is well documented and flexible, so you can build any dApp you can imagine. From the way the code is written to the way…
2022 · mesh.martify.io
Ranked by how close each launch is in meaning, then by votes. Refine with a description →