Life & fun · alternatives · 2026
24 alternatives to A Transformer model that preserves logical equivalence
Optimize logic circuits by minimizing their size while preserving logical equivalence. Provide a logic circuit in Aiger format with up to 8 inputs and 2 outputs, and specify the number of Monte-Car...
Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes.
- 1
I replicated David Ng's RYS method (https://dnhkng.github.io/posts/rys/) on consumer AMD GPUs (RX 7900 XT + RX 6950 XT) and found something I didn't expect. Transformers appear to have discrete "reasoning circuits" — contiguous blocks of 3-4 layers that act as indivisible cognitive units. Duplicate the right block and the model runs its reasoning pipeline twice. No weights change. No training. The model just thinks longer. The results on standard benchmarks (lm-evaluation-harness, n=50): Devstral-24B, layers 12-14 duplicated once: - BBH Logical Deduction: 0.22 → 0.76…
Mar 2026 · github.com · its alternatives →
- 2
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 · its alternatives →
- 3IM
Building a 10BASE-T Ethernet transceiver (receiver and transmitter) with discrete logic chips
2024 · qdiv.dev · its alternatives →
- 4
Zero-Knowledge Proofs (ZKPs) let an untrusted proved show that computation was executed correctly without revealing the inputs to the verifier. However to prove anything, the computation first has to be expressed as a circuit: a system of polynomial equations (constraints) over a finite field. Circuits are the assembly language of zk and every constraint costs prover (and sometimes verifier) time, so production circuits are aggressively hand-optimized. Over the last months, we have been experimenting with writing formal specifications instead and letting LLMs produce the circuits: as long as…
Jul 2026 · zk.golf · its alternatives →
- 5AB
I built AutoThink, a technique that makes local LLMs reason more efficiently by adaptively allocating computational resources based on query complexity. The core idea: instead of giving every query the same "thinking time," classify queries as HIGH or LOW complexity and allocate thinking tokens accordingly. Complex reasoning gets 70-90% of tokens, simple queries get 20-40%. I also implemented steering vectors derived from Pivotal Token Search (originally from Microsoft's Phi-4 paper) that guide the model's reasoning patterns during generation. These vectors encourage behaviors like numerical…
2025 · its alternatives →
- 6
Hi HN, I've been exploring various applications of formal methods to ML/interpretability and I've been hoping to get more eyes on the approach. I have been working on a small interpretability project I call Symbolic Circuit Distillation. The goal is to take a tiny neuron-level circuit (like the ones in OpenAI's "Sparse Circuits" work) and automatically recover a concise Python program that implements the same algorithm, along with a bounded formal proof that the two are equivalent on a finite token domain. Roughly, the pipeline is: 1. Start from a pruned circuit graph for a specific…
Jan 2026 · github.com · its alternatives →
- 7
A chess engine implementation inspired by AlphaZero, using MLX for neural network computations and Monte Carlo Tree Search (MCTS) for move selection.
2025 · github.com · its alternatives →
- 8
This is a little toy project of mine that lets you simulate digital logic graphs. It was inspired by Minecraft's Redstone and the Piet esolang. It's got some serious drawbacks-- you write circuits as PNGs and simulate them with a Python interface. It's slow to run and slow to experiment with. And it is certainly difficult to use for people with any kind of color blindness. But despite that, I hope this can still be a fun toy!
2022 · github.com · its alternatives →
- 9
Hi! me and my friends together built an 8 bit CPU implemented in Logisim purely from scratch. The control unit of this system does not implement the generic microcode ROM or any kind of RAM. This was made purely from discrete logic gates and coded the system to run different programs. key features: Custom 16-instruction Harvard ISA, 8-bit fixed format, 4 general purpose registers Hardwired control unit built entirely from AND/OR gate logic matrix Dual-phase clocking to eliminate race conditions Bootstrap Control Unit that cold-boots via ROM-to-RAM transfer Early-exit conditional…
Jun 2026 · github.com · its alternatives →
- 10
Haskell re-implementation of STOKE, the stochastic superoptimizer - blaze/notebooks/tutorial.ipynb at master · bollu/blaze
2019 · github.com · its alternatives →
- 11AT
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.
Aug 2026 · mikeayles.com · its alternatives →
- 12
Inspired by games like Turing Complete/Virtual Circuit Board/Logic World, I tried to make a mix of aseprite and wiredworld/wired-logic, the idea being the user can build a digital circuit using a "fullstack" pixelart creation workflow. The circuit is just an image. The primitives are (i) connected wires which have undefined, 0 or 1 state during simulation (displayed brighter or darker in function of the state) and (ii) NANDs, which are little pixel triangles. During simulation the user can interact with any wire by clicking on it, toggling its state, which is cool for messing…
2024 · github.com · its alternatives →
- 13BA
2017 · boolr.me · its alternatives →
- 14
Fine-tuning, RL, and inference in one CLI
Dec 2025 · github.com · its alternatives →
- 15
- 16
Open-source logic circuit simulator with AI assistant
Feb 2026 · logicdrawer.app · its alternatives →
- 17
Instantly Create Digital Logic Circuits with AI
2025 · circuitai.vercel.app · its alternatives →
- 18
Automatically interpret and validate nested natural logic arguments based on rules of inference and propositional logic - ParhamP/Natural_Logic_Interpreter
2017 · github.com · its alternatives →
- 19IB
We had no guide or course that teaches chip design at our university. We had taken a digital logic course, but were disappointed with the fact that the most complex project we did was building a full adder in Quartus using logic blocks, not even in RTL!5 Therefore, we decided to challenge ourselves to dive deep into machine learning (ML) hardware and learn as much as we could on our own. We wanted to prove that basic math (like y = mx + b) and basic logic circuits are enough to help anyone understand how modern AI hardware works. Our goal was to design our own version of the LPU from scratch…
Aug 2026 · lpulite.com · its alternatives →
- 20
A complete transformer engine in C — inference, training, chat, vision. - carlovalenti/TRiP
Apr 2026 · github.com · its alternatives →
- 21
Fast equality saturation in Haskell
2022 · hackage.haskell.org · its alternatives →
- 22
Use EEPROM chips as programmable logic. Contribute to DusteDdk/eepromlogic development by creating an account on GitHub.
2023 · github.com · its alternatives →
- 23
Hey HN, My co-author and I just published a paper on arXiv that formalises a framework we've been using successfully in probabilistic logic for many years. We decided it was time to properly lay out its foundations for classical propositional logic. We cast propositional logic into a formal algebra where logical formulas are represented by sparse matrices. State Algebra isn't an algorithm in itself, but rather a language for manipulating Boolean functions. It provides a new set of tools that lets you express and reformulate existing optimization heuristics (like those from modern SAT…
2025 · arxiv.org · its alternatives →
- 24
TLDR: A small, vendor-agnostic inference loop that turns token logprobs/perplexity/entropy into an extra pass and reasoning for LLMs. - Captures logprobs/top-k during generation, computes perplexity and token-level entropy. - Triggers at most one refine when simple thresholds fire; passes a compact “uncertainty report” (uncertain tokens + top-k alts + local context) back to the model. - In our tests on technical Q&A / math / code, a small model recovered much of “reasoning” quality at ~⅓ the cost while refining ~⅓ of outputs. I kept seeing “reasoning” models behave…
2025 · github.com · its alternatives →
Also compare
- Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training alternatives
- I built a tiny LLM to demystify how language models work alternatives
- I made a discrete logic network card alternatives
- zkGolf – Competitive optimization of formally verified circuits alternatives
- AutoThink – Boosts local LLM performance with adaptive reasoning alternatives
- Symbolic Circuit Distillation: prove program to LLM circuit equivalence 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 →