AI · alternatives · 2026
24 alternatives to We trained a 32B model to beat Opus 4 at credit card optimization
We built an RL environment for credit card reward optimization and trained Qwen 32B with GRPO against it. The trained model scores ~0.51 on held-out tasks vs. Opus 4 at ~0.41 and GPT-4o at 0.36. Environment is open source (Apache 2.0). Blog post explains the reward design, what broke during training, how we fixed it, and what we'd do differently.
Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes.
- 1
Hi HN! I'm just sharing a project I've been working on during the LLM Efficiency Challenge - you can now finetune Llama with QLoRA 5x faster than Huggingface's original implementation on your own local GPU. Some highlights: 1. Manual autograd engine - hand derived backprop steps. 2. QLoRA / LoRA 80% faster, 50% less memory. 3. All kernels written in OpenAI's Triton language. 4. 0% loss in accuracy - no approximation methods - all exact. 5. No change of hardware necessary. Supports NVIDIA GPUs since 2018+. CUDA 7.5+. 6. Flash Attention support via Xformers. 7. Supports 4bit and 16bit…
2023 · github.com · its alternatives →
- 2
After training calculator agent via RL, I really wanted to go bigger! So I built RL infrastructure for training long-horizon terminal/coding agents that scales from 2x A100s to 32x H100s (~$1M worth of compute!) Without any training, my 32B agent hit #19 on Terminal-Bench leaderboard, beating Stanford's Terminus-Qwen3-235B-A22! With training... well, too expensive, but I bet the results would be good! *What I did*: - Created a Claude Code-inspired agent (system msg + tools) - Built Docker-isolated GRPO training where each rollout gets its own container - Developed a multi-agent…
2025 · github.com · its alternatives →
- 3IB
This is a free tool that helps you manage and visualize your credit card rewards across different categories. You can input the cards in your wallet and see how they complement each other, spot gaps in your setup, and also see the best card to use for a given merchant. I’m also a founder at OneCard, where we’re building a smart card that’ll eventually handle all of this automatically, routing each purchase to the best card in real-time. Would love feedback from the HN community!
2025 · rewards.getonecard.io · its alternatives →
- 4
We recently used DeepSeek V4 Flash as a teacher for finance tasks with GPT-OSS-120B. Distillation works well on this problem. At a constrained 8k token budget, our self-distilled 120B scores 83.61% on FinanceReasoning, above Kimi K3 (81.93%) and Inkling (65.13%). We released the 20B open weights. With V4 as the teacher though, we realized it would be timely to measure if the censorship characteristic of it transferred to the distilled version of the base model. tl;dr it didn't, the teacher answered politically sensitive questions 7 SDs differently than expected, but the distilled model's…
Jul 2026 · ctgt.ai · its alternatives →
- 5
I worked on this applied Deep Reinforcement Learning course for the better part of 2021. I made a Datacamp course [0] before, and this served as my inspiration to make an applied Deep RL series. Normally, Deep RL courses teach a lot of mathematically involved theory. You get the practical applications near the end (if at all). I have tried to turn that on its head. In the top-down approach, you learn practical skills first, then go deeper later. This is much more fun. This course (the first in a planned multi-part series) shows how to use the Deep Reinforcement Learning framework RLlib to…
2022 · courses.dibya.online · its alternatives →
- 6
Qwen3.6-35B-A3B▲124The open sparse MoE model for agentic coding
Apr 2026 · qwen.ai · its alternatives →
- 7AG
This is a vector index I built that supports insertion and k-nearest neighbors (k-NN) querying, optimized for GPUs. It operates entirely in CUDA and can process queries on half a billion vectors in under 200 milliseconds. The codebase is structured as a standalone library with an HTTP API for remote access. It’s intended for high-performance search tasks—think similarity search, AI model retrieval, or reinforcement learning replay buffers. The codebase is located at https://github.com/rodlaf/BinaryGPUIndex.
2025 · rlafuente.com · its alternatives →
- 8
Cardzen▲92Track every credit, perk, and point before it expires
Jul 2026 · cardzen.ai · its alternatives →
- 9
delegare▲70Hi guys, am building SecureLend.ai and when working on our underwriting agents (free trial, paid after) I had issues with seamless payment options. Of course I looked at x402 which I believe is a great protocol but not a fan of a) sharing private keys with the agent b) having a human in the loop or c) similar workaround e.g. pre-funded wallets So I started building out a solution. For my use case it was important to not only have stablecoins but also a fiat rail which is now implemented using Stripe. Initially I build a mandate system internally but am very glad and big shoutout to the guys…
Apr 2026 · delegare.dev · its alternatives →
- 10
Minimal, readable LLM post-training experiments on one 8GB GPU. Measures forgetting, seed variance, and RL emergence. - pochenai/nano-llm-posttraining
Aug 2026 · github.com · its alternatives →
- 11
We're excited to announce that we've open-sourced LeanRL, a lightweight PyTorch reinforcement learning library that provides recipes for fast RL training using torch.compile and CUDA graphs. By leveraging these tools, we've achieved significant speed-ups compared to the original CleanRL implementations - up to 6x faster! Reinforcement learning is notoriously CPU-bound due to the high frequency of small CPU operations. PyTorch's powerful compiler can help alleviate these issues, but comes with its own costs. LeanRL addresses this challenge by providing simple recipes to accelerate your…
2024 · github.com · its alternatives →
- 12
Arc enables continual learning for agents to adapt, learn, and transfer knowledge in live environments. Open-source SDK for building agents that learn from experience and improve over time.
2025 · arc.computer · its alternatives →
- 13
I wanted to know how fast a 26B mixture-of-experts model could run on a desktop CPU with no GPU. Got ~40 tok/s single-stream (lossless) and ~124 batched. The surprising part was the byte budget: for this model you compress the output head (32% of per-token bytes), not the experts (16%). The writeup has the bandwidth roofline and the dead-ends; the repo has the reproducible recipe. Happy to answer questions. Repo: https://github.com/arun-prasath2005/gemma4-cpu-moe
Jun 2026 · apeg.dev · its alternatives →
- 14
It took me about a week to vibe code this 3D game engine with Opus 4.6 that I intend to use as a replacement for Three.js and React Three Fiber in my browser MMORPG, Mana Blade. I was not expecting to be able to reach that point so easily, but pretty much every feature took somewhere between 30 minutes and 1 hour - 1 to 3 prompts on average. It is vibe-coded in the sense that I haven't looked at the code, but I am very careful with my prompts and constantly have Claude reviewing the codebase, looking for performance and code quality improvements. It can reach 2000 draw calls on recent…
Feb 2026 · github.com · its alternatives →
- 15
Stop guessing which card to use. Let your bank data decide.
Apr 2026 · getpoiiints.com · its alternatives →
- 16
CCProxy▲13Keep Claude Code's magic, slash costs by 90%
2025 · ccproxy.orchestre.dev · its alternatives →
- 17
I built this mostly because I love the intersection of game AI, high-performance computing, and poker. I’d love for anyone interested in game theory or CUDA optimization to tear it apart, test the accuracy, and give me feedback. Happy to answer any questions about the algorithms, the transition from CPU to GPU, or poker AI in general!
Jul 2026 · bupticybee.github.io · its alternatives →
- 18
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 · its alternatives →
- 19IM
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 · its alternatives →
- 20
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 · its alternatives →
- 21
Claude Code Companion. Done, Blocked, Broken - you'll know
May 2026 · thecodebreak.com · its alternatives →
- 22BA
I built CodeLens.AI - a tool that compares how 6 top LLMs (GPT-5, Claude Opus 4.1, Claude Sonnet 4.5, Grok 4, Gemini 2.5 Pro, o3) handle your actual code tasks. How it works: - Upload code + describe task (refactoring, security review, architecture, etc.) - All 6 models run in parallel (~2-5 min) - See side-by-side comparison with AI judge scores - Community votes on winners (blind voting) - Each evaluation gets reflected in the overall AI model leaderboard, showing us best ones Why I built this: Existing benchmarks (HumanEval, SWE-Bench) don't reflect real-world developer tasks. I wanted to…
2025 · codelens.ai · its alternatives →
- 23HT
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 · its alternatives →
- 24
Howdy friends. I've been a zero to one product manager for 12 plus years and along the way I kept borrowing pieces from different discovery frameworks until I had a methodology of my own, one that actually raises the odds of an idea succeeding. This does not replace user interviews obviously, but it leads you in the right direction. Looking forward for your feedback
Jul 2026 · github.com · its alternatives →
Also compare
- 80% faster, 50% less memory, 0% loss of accuracy Llama finetuning alternatives
- Terminal-Bench-RL: Training long-horizon terminal agents with RL alternatives
- I built a tool to manage and compare credit card rewards alternatives
- Distilling DeepSeek into GPT-OSS doesn't transfer censorship. Try it alternatives
- Fast Deep Reinforcement Learning Course alternatives
- Qwen3.6-35B-A3B alternatives
Ranked by how close each launch is in meaning, then by votes. Prices were read from each product’s own site when checked and can change. Refine with your own description →