An ESP32-S3 microcontroller now runs a Neural Amp Modeler A2-Lite capture natively in single-precision float, producing bit-identical output to a desktop render, with all 720,000 samples matching by h…
A developer focused on improving the YM2151 firmware, addressing clock control, Wi-Fi startup issues, and adding a 3DGS learning environment with Japanese materials and SH visualization. The work incl…
An independent research project demonstrated that three ESP32-S3 microcontrollers can jointly compute Graph Neural Network inference on traffic data using Replicated Secret Sharing, ensuring no single…
An independent researcher demonstrated that timing side channels in multi-agent reinforcement learning (MARL) policies deployed on microcontrollers can leak information about an agent's next action. B…
Makerfabs released the MaTouch ESP32-S3 MaUWB development board, which combines an ESP32-S3 wireless MCU, a 3.95-inch touchscreen, and a UWB module for indoor positioning and ranging. The board uses a…
A developer trained a small language model from scratch on an $8 ESP32-S3 microcontroller, demonstrating that training, not just inference, is possible on ultra-low-cost hardware. The project, inspire…
Slava S. (slvDev) has optimized a 28.9M-parameter LLM to run locally on an ESP32-S3 development board at about 9 tokens/s, generating short stories on an I2C display. The project, called 'esp32-ai', r…
A 27-million-parameter reasoning model that runs entirely offline on two ESP32-S3 microcontrollers, costing about $40 in hardware, achieves 85.5% accuracy on unseen comparative adjectives, up from 63.…
A developer released a shell script that lets users test custom prompts against an already-trained ESP32-S3 model without retraining or rewriting the 15MB model partition. The script tokenizes the pro…
A developer has released a one-shot build script that automates the entire pipeline for running a 28M parameter AI model on an ESP32-S3 microcontroller, from cloning the repository to training, export…
A developer ran a 56M-parameter language model across three ESP32-S3 N16R8 microcontrollers using ESP-NOW wireless communication, achieving distributed inference of a 50.3M-parameter PLE-based transfo…
Anthropic announced it cut Claude Code's system prompt by more than 80% for the Claude 5 generation with no measurable regression on coding evals, urging developers to rely less on prompt engineering.…
A developer known as slvDev has run a 28.9-million-parameter language model on an ESP32-S3 microcontroller, an $8 chip with 512KB of SRAM, achieving 9.5 tokens per second for offline text generation. …
A developer known as slvDev has run a 28.9 million parameter language model on an ESP32-S3 microcontroller that costs about $8, generating text at roughly 9.5 tokens per second entirely on-device. The…
A developer known as slvDev_ has run a small language model on an Espressif Systems ESP32-S3 microcontroller costing under $8, using a technique called Per-Layer Embeddings to store most of the 28.9-m…
A developer has created WiFi-LLM, a system that runs a Llama-2-architecture model on an ESP32 microcontroller by streaming weights from a PC over WiFi, keeping the ESP32's RAM usage flat at around 110…
The Device Context Protocol (DCP) v0.3, hardware-validated on ESP32-WROOM-32 and ESP32-S3 boards, enables LLM agents to safely control physical devices using sub-50-byte frames and under 1 KB of RAM. …
A developer proposed PAL, an open standard that gives AI agents direct control over physical hardware via a Python REPL running on an ESP32-S3. The architecture splits real-time safety-critical operat…
M5Stack and its user community co-created StackChan, a kawaii AI desktop robot powered by an ESP32-S3 SoC with features including a 2.0-inch touch display, camera, servos, RGB LEDs, and NFC. The robot…
Two ESP32-S3 microcontrollers running a Llama-architecture language model have achieved the first multi-chip pipelined LLM inference on ESP32-class hardware, splitting layers across two boards connect…