Explore tools, prompts, skills, news and resources related to AI 第77页.
Prompt works related to AI 第77页
Latest articles, prompts, use cases and editorial content about AI 第77页
This article compares routing mechanisms across 10 open Mixture-of-Experts (MoE) models, detailing expert counts, top-k values, shared experts, gating functions, and load-balancing methods. It highlights trends like grow...
Google has released the Elephant-Goldfish Model (EGM) plugin, an Apache 2.0 open-source tool that enforces a spec-first workflow for AI coding agents. It uses a deep-context 'Elephant' agent to draft specificat...
Apiiro found that Claude Code's "don't ask again" option saved approved commands, including credentials, to a local settings file. The firm counted 2,539 secrets across 1,994 public repositories, with...
METR estimated that Anthropic’s AECI benchmark scores are improving at 1.9 times the earlier rate. The reported 95% interval ranges from 1.5× to 2.8×, while the extent to which AI itself explains the acceleration remains...
Alibaba introduced Co-Design Bench, a benchmark based on real user requests that coding agents previously failed in practice. The top-performing model, GPT-6 Astra, fully solved 26.4% of tasks, despite the same models sc...
Nous Research released Arete-27B, a supervised fine-tune of Qwen3.8-27B trained on 52.8 million tokens without reinforcement learning or architectural changes. On Nous Research's self-built 803-prompt evaluation, th...
OpenAI has introduced GPT-6 Cyber for authorized vulnerability research, reporting results involving Linux, Firefox and scope tests. Initial access through the API and Codex was limited to selected Daybreak Red customers...
Apiiro found 379 database passwords, 43 SSH logins and 23 AWS keys in public copies of a Claude Code settings file linked to the “Don’t Ask Again” option. Gitleaks and TruffleHog reportedly missed 215 of the secrets, whi...