Roboflow's MIT-licensed Supervision computer vision library crossed 50,000 GitHub stars and claims over 1 million PyPI downloads per month, following its 0.30.3 release on September 14, the fourth rel…
OpenBMB shipped VoxCPM2, a 2B-parameter text-to-speech model that generates speech directly in a continuous latent space with no discrete audio tokens, covering 30 languages from raw text without a ph…
A developer tutorial by Priya Nair shows how to build a self-hosted real-time speech-to-text pipeline using faster-whisper 1.2.1 and websockets 17.1, streaming 16 kHz mono PCM audio from a browser mic…
Hugging Face released Transformers v5.17.0 on September 9, adding seven model architectures in a single minor release, including Tencent's 780-billion-parameter mixture-of-experts model and Moonshot A…
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…
Promptfoo 0.122.2 can be wired into GitHub Actions to run an eval suite against a golden dataset on every pull request that touches prompts, failing the CI check when outputs regress and posting a bef…
Anthropic's March 2023 'Core Views on AI Safety' essay has become a de facto roadmap for AI safety enforcement, with its principles now embedded in API specifications and deployment policies. The essa…
Anthropic's July 2023 biosecurity red-teaming exercise has become the industry's default procedure for frontier AI safety, but most teams copying it skip critical steps such as testing raw models with…
Anthropic's 2023 wishlist for AI accountability, filed with the NTIA, has largely been fulfilled three years later, but through state law and the EU AI Act rather than federal action, according to a r…
Google's open-source, JAX-native post-training library Tunix now ships an agentic RL trainer built around asynchronous rollouts and a decoupled producer-consumer pipeline, aiming to eliminate idle TPU…
A developer guide published on Sourcefeed by Ji-ho Choi demonstrates how to run untrusted LLM-generated code inside a gVisor sandbox using Docker's runsc runtime, verified against gVisor release 20260…
Ray 2.55 adds official TPU support with atomic gang scheduling for TPU slices, aiming to cut GPU costs by enabling Ray-based workloads to run on Google's TPUs. Google's motive is to boost external TPU…
A GitHub repository called text-to-cad, created by software engineer Jake Fitzgerald, has reached 14,800 stars and 1,500 forks by turning mechanical design into a coding-agent problem. The MIT-license…
Priya Nair published a tutorial showing developers how to rewrite weak prompts into stable classifiers using zero-shot, few-shot, and chain-of-thought patterns, with runnable Python code verified agai…
OpenAI's openai/plugins repository, with about 5,600 GitHub stars, shows coding-agent extensions converging on the plugin format Anthropic shipped first, featuring `.codex-plugin/plugin.json` manifest…
A GitHub skill called i-have-adhd, created by user ayghri, has amassed 28,000 stars and 1,800 forks since May by instructing coding agents to format responses for readers with ADHD, leading with next …
A tutorial by Rachel Goldstein demonstrates how to regression-test LLM prompts using promptfoo 0.122.2 in GitHub Actions, catching prompt and model regressions on every pull request. The setup include…
Emeka Okafor published a guide for sandboxing untrusted AI-generated Python code using gVisor's user-space kernel, demonstrating a Docker-based setup with no network, no capabilities, and hard CPU, me…
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…
Everything Claude Code (ECC), a configuration framework for AI coding agents created by Affaan Mustafa, has reached roughly 249,000 GitHub stars in under eight months, making it one of the fastest-gro…