Alternatives
Products that do what Semantic Overlays – an NX bit for LLM prompt injection (live demo) does
Tiny adapters added to a frozen language model. They only fire at marked token positions, and they change how the model perceives those spans.
- 1IB
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
Apr 2026 · github.com
- 2WT
After working with LLMs for long enough, I found myself wanting a lightweight utility for doing various small tasks to prepare inputs, locate information and create evaluators. This library is two things: a very simple model and utilities that inference it (eg. fuzzy deduplication). The target platform is CPU, and it’s intended to be light, fast and pip installable — a library that lowers the barrier to working with strings semantically. You don’t need to install pytorch to use it, or any deep learning runtimes. How can this be accomplished? The model is simply token embeddings that are…
2024 · github.com
- 3
- 4TV
May 2026 · github.com
- 5
- 6TD
This is a character-level language diffusion model for text generation. The model is a modified version of Nanochat's GPT implementation and is trained on Tiny Shakespeare! It is only 10.7 million parameters, so you can try it out locally.
Nov 2025 · github.com
- 7AT
A 3.16M-parameter INT4 transformer running entirely in the on-chip memory of a Xilinx Kria KV260. Zero DRAM in the token loop, 59,965 tok/s on the fabric, bit-exact. Chat with it live.
27d ago · mikeayles.com
- 8PE
Nowadays, a common AI tech stack has hundreds of different prompts running across different LLMs. Three key problems: - Choices, picking from 100s of LLMs the best LLM for that 1 prompt is gonna be challenging, you're probably not picking the most optimized LLM for a prompt you wrote. - Scaling/Upgrading, similar to choices but you want to keep consistency of your output even when models depreciate or configurations change. - Prompt management is scary, if something works, you'll never want to touch it but you should be able to without fear of everything breaking. So we launched Prompt…
2024 · jigsawstack.com
- 9TA
Jun 2026 · github.com
- 10
- 11TL
I'm building this resource to dive deeper into "TypeLeap," a UI/UX concept where interfaces dynamically adapt based on as-you-type intent detection. Seeking real-world examples of intent-driven UIs in the wild and design mock-ups! Design inspiration & contributions especially welcome.
2025 · typeleap.com
- 12IR
The Emotion Engine has 32 MB of RAM total, so the trick is streaming weights from CD-ROM one matrix at a time during the forward pass — only activations, KV cache and embeddings live in RAM. This means models bigger than the RAM can still run, they just read more from disc. Had to build a custom quantized format (PSNT), hack endianness, write a tokenizer pipeline, and most of the PS2 SDK from scratch (releasing that separately). The model itself is also custom — a 10M param Llama-style architecture I trained specifically for this. And it works. On real hardware.
Mar 2026 · github.com
- 13RL
May 2026 · adola.app
- 14RA
Hey everyone! Along with my team, I've developed a reinforcement learning system that automatically optimizes LLM prompts, complete with a visualization feature to track both prompt structure and learning progress over time. Take a look here: https://nomadic-ml.github.io/nomadic/cookbooks/Nomadic_Promp... Check out our website too:https://www.nomadicml.com/ In terms of how this visualization works: The RL Prompt Optimizer employs a reinforcement learning framework to iteratively improve prompts used for language model evaluations. At each episode, the…
2024 · nomadic-ml.github.io
- 15PA
Hey HN! We just launched PromptL: a templating language built to simplify writing complex prompts for LLMs like GPT-4 and Claude. Why PromptL? Creating dynamic prompts for LLMs can get tricky, even with standardized APIs that use lists of messages and settings. While these formats are consistent, building complex interactions with custom logic or branching paths can quickly become repetitive and hard to manage as prompts grow. PromptL steps in to make this simple. It allows you to define and manage LLM conversations in a readable, single-file format, with support for control flow and…
2024 · promptl.ai
- 16CL
Hi HN! Run it: OPENROUTER_API_KEY="sk" npx bff-eval --demo We built a tool to help people take LLM outputs and easily grade them / eval them to know how good an assistant response is. We've built a number of LLM apps, and while we could ship decent tech demos, we were disappointed with how they'd perform over time. We worked with a few companies who had the same problem, and found out scientifically building prompts and evals is far from a solved problem... writing these things feels more like directing a play than coding. Inspired by Anthropic's constitutional ai concepts, and amazing…
2025 · github.com
- 17PR
Apr 2026 · preprompt.org
- 18ZA
Hi everyone, I've made an early version of ZigFormer, a small LLM implemented in Zig with no dependencies on external ML frameworks like PyTorch or JAX. ZigFormer is modelled after a textbook LLM (like GPT-2 from OpenAI) and can be used as a Zig library as well as a standalone application to train a model and chat with it. This was mainly an educational project. I'm sharing it here in case others find it interesting or useful. Link to the project: https://github.com/CogitatorTech/zigformer
Nov 2025
- 19
Token-efficiency linter for LLM prompts and payloads - ritenv/tokensift
8d ago · github.com
- 20PR
Hi HN, While building RAG agents, I noticed a lot of token budget was wasted on formatting overhead (HTML tags, JSON structure, whitespace). Existing solutions felt too heavy (often requiring torch/transformers), so I wrote this lightweight, zero-dependency library to solve it. It includes strategies for context packing, PII redaction, and tool output compression. Benchmarks show it can save ~15% of tokens with negligible latency overhead (<0.5ms). Happy to answer any questions!
Dec 2025 · github.com
- 21ML
Aug 2026 · github.com
- 22AA
An all-in-one blog for learning LLM ins and outs: tokenize, attention, PE, and more Project I've been diving deep into the internals of Large Language Models (LLMs) and started documenting my findings. My blog covers topics like: Tokenization techniques (e.g., BBPE) Attention mechanism (e.g. MHA, MQA, MLA) Positional encoding and extrapolation (e.g. RoPE, NTK-aware interpolation, YaRN) Architecture details of models like QWen, LLaMA Training methods including SFT and Reinforcement Learning If you're interested in the nuts and bolts of LLMs, feel free to check it out:…
2025 · comfyai.app
- 23K6
Hey Hacker News! We are excited to share the new version of KTransformers, a flexible framework designed for cutting-edge LLM inference optimizations! Leveraging state-of-the-art kernels from llamafile and marlin, KTransformers seamlessly enhances the performance of HuggingFace Transformers, making it possible to operate large 671B MoE models or extremely long 1M context locally with promising speed. KTransformers is a Python-centric framework designed with extensibility at its core. By implementing and injecting an optimized module with a single line of code, users gain access to a…
2025 · github.com
- 24AE
2025 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →