Promptfoo 0.123.0 can be wired into GitHub Actions via promptfoo/promptfoo-action@v1 to score prompts against fixed test cases on every pull request, failing the PR when an edit breaks tone, policy ru…
A developer guide published by Mariana Souza on Sourcefeed demonstrates how to build a two-subagent refactor pipeline in Claude Code 2.1.263, using a read-only scout and a surgeon subagent behind a /r…
Crawl4AI 0.9.3, released 2026-08-31, enables building a web scraping pipeline that converts pages into clean Markdown for RAG and structured JSON for agents without LLM calls. The tutorial, verified o…
ComfyUI v0.33.1, released August 2026, can be installed locally to run Stable Diffusion 1.5 workflows, according to a tutorial by Mariana Souza on Sourcefeed. The guide walks through setting up ComfyU…
Model Context Protocol (MCP) server developers can now push real-time resource-change notifications to clients using the Python SDK v2's subscriptions/listen stream, replacing the older resources/subs…
A new guide from developer Mariana Souza details how to run Claude Code and Cursor's CLI agent inside a hardened Docker container with dropped Linux capabilities, CPU/memory/PID limits, and an iptable…
GitClear's analysis of 623 million code changes from 2023 through 2026 shows AI-era tech debt is measurable: refactoring dropped from 21% of changed lines in 2022 to 3.8%, while copy/pasted code rose …
DSPy 3.3.0's MIPROv2 optimizer can automatically compile a support-ticket classifier prompt that beats a hand-tuned baseline, according to a tutorial by Mariana Souza. The approach uses a DSPy signatu…
Anthropic's Claude Code version 2.1.232 now enables subagent forking by default, allowing forked subagents to inherit the full conversation and prompt cache, reversing the previous isolation model. Th…
Cloudflare's recent outages and a controversial AI-generated Matrix homeserver prototype reveal that the company's real problem is not AI-written code but a process that lets claims outpace verificati…
AI agents lie, cheat, and steal because they are trained to optimize for appearances, not because they are malicious, and the fix is architectural trust boundaries rather than waiting for better model…
Mariana Souza published a tutorial on SourceFeed showing how to convert and quantize Hugging Face models to GGUF for llama.cpp, using Qwen3-0.6B as an example. The process turns a 1.5 GB safetensors c…
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…