Mistral AI's Mixtral 8x7B mixture-of-experts model can be run locally using llama.cpp build b10261, with generation speed tracking its ~12.9B active parameters while memory usage tracks all 46.7B para…
Manifest, an open-source development platform, shipped an LLM router in March 2024, saw 7,000 cloud users use it for four months, and deprecated it in June, with full shutdown on September 1. The comp…
OpenAI open-sourced the CLI and TypeScript SDK for its agentic vulnerability scanner Codex Security on July 28 under Apache-2.0, but every scan still runs on OpenAI's hosted models authenticated via a…
Feyn Labs released FeyNoBg, a 263M-parameter background-removal model that leads on four of eight standard benchmarks and stays within 2% of the leader on the rest, but the weights are licensed CC-BY-…
A tutorial by Mariana Souza demonstrates how to classify text sentiment in 10 lines of Python using a Hugging Face Transformers pipeline with a pretrained DistilBERT model, running entirely on CPU wit…
Cisco's new Antares-1B open-weight model for vulnerability localization tied GPT-5.5 on the company's VLoc Bench with a 0.221 F1 score while costing $1 versus $141 for the frontier model, but the best…
Researchers are applying causal mediation analysis and interventions to reverse-engineer large language models into debuggable circuits, enabling teams to localize why a model fails and sometimes edit…
Claude Code consumes approximately 33,000 tokens in system prompts, tool schemas, and scaffolding on its first request, compared to OpenCode's 7,000 tokens, a 4.7× overhead that increases session cost…
Mariana Souza published a practical guide for fine-tuning Qwen2.5-7B-Instruct using QLoRA on custom instruction datasets, including cost estimates and a loss-masking sanity check. The tutorial covers …
OpenAI's experimental Swarm framework enables developers to build a multi-agent customer support system that routes requests between specialist agents. The system uses a topic guardrail to filter irre…
Mariana Souza published a tutorial on quantizing and running Meta's Llama 3.2 3B model on Apple Silicon using llama.cpp with Metal GPU acceleration, achieving local inference with Q4_K_M quantization.…
Google's Gemini 1.5 Flash multimodal API can now analyze images and PDFs in Python, returning structured JSON. A new script demonstrates sending a local JPEG and PDF to the model and parsing the respo…