MDev

Honestly don't know what happened to Claude Code. Tried a one-off simple task on a fresh directory yesterday, tried a bunch of things that didn't work, asked for a ton of permissions, and then got stuck for 4 minutes before I got tired of waiting and killed the session. This was on medium effort. Switched to Codex gpt 5.4 with medium effort and one shotted the task in under 1 minute.

In Elysia 2 Elysia adapter is available for general usage The current Elysia adapter is for internal usage only, which is a code string instruction for Elysia "compiler" In Elysia 2, we make it much easier to write your own adapter

Introducing MMX-CLI — our first piece of infrastructure built not for humans, but for Agents. Your Agent can read, think, and write. But ask it to sing, paint, or show you a world it's never seen — and it falls silent. Not because it doesn't understand, but because it has no mouth, no hands, no camera. Today, that changes. MMX-CLI gives every Agent seven new senses — image, video, voice, music, vision, search, conversation — powered by MiniMax's full-modal stack, today's SOTA across mainstream omni-modal models. One command: mmxAgent-native I/O. Zero MCP glue. Runs on your existing Token Plan. Two lines to give your Agent a voice: npx skills add MiniMax-AI/cli -y -g npm install -g mmx-cli Then tell it: "you have mmx commands available." It'll learn the rest. Github → github.com/MiniMax-AI/cli Token Plan: platform.minimax.io/subscribe/toke…

Yeah folks, it's gonna be harder in the future to ensure OpenClaw still works with Anthropic models.

🚀 Qwen Code v0.14.0 – v0.14.2 are now available Channels：Control Qwen Code remotely from Telegram, DingTalk, or WeChat — send a message from your phone, get results on your server Cron Jobs ：Schedule recurring AI tasks — auto-run tests every 30 min, pull & build every morning, monitor logs on a timer Qwen3.6-Plus ：New flagship model with 1M token context, 1,000 free daily requests Sub-agent Model Selection：Assign different models to sub-agents — use a powerful model for the main task, a fast one for subtasks, save tokens without sacrificing quality /plan：Enter planning mode before execution — AI maps out all files and steps first, you confirm, then it executes Follow-up Suggestions：AI suggests 2-3 next steps after completing a task — "Add unit tests?" "Check similar files?" — click to continue Adaptive Output Tokens ：Default 8K output, auto-escalates to 64K when truncated — no more manually tuning max_tokens Ctrl+O Verbosity Toggle ：Switch between verbose and compact output mid-conversation — debug mode when you need it, clean mode when you don't 📋 Full changelog: github.com/QwenLM/qwen-co…

Sam Altman’s coworkers say he can barely code, so his AGI safety plan is just “thoughts and prayers” in Python.

Your chance to get my Coding with AI course for free, courtesy of @neondatabase 🙏

I'm loving the 100% uptime of the Server Side Up website 🤓 It's all running on an old gaming rig from 2019 on a 35 mbps connection. And we're all told we can only get this through multiple AWS Regions & Zones 💸💸💸

@carre_sam @jaydrogers recently ditched virgin media for community fibre and my homelab is thriving, proxmox containers running postgres replica + some client's legacy system, no static ip, just cloudflare tunnels + tailscale doing the heavy lifting 💪

@jaydrogers Self hosting / on prem is so underrated. I've just setup a home proxmox cluster for managing my VMs and it has had incredible uptime, even with standard residential fibre oh and no static IP, all managed with Cloudflare Tunnels & Tailscale

MUI v9 release is here 🚀 This release changes how we ship major versions. We shipped new features and components on a coordinated major across Material UI and MUI X with one goal: make your workflows easier to build, upgrade, and scale. Highlights and links below 👇

TanStack AI now ships with native skills directly in the NPM module. 🔒 Versioned & trusted 🔗 Updated with source code 🧠 TanStack Intent compatible Fastest way to try them? ⬆️ Upgrade @ tanstack/ai (and friends) 📲 Tell your agent to run: npx @tanstack/intent@latest install

We’ve updated our pricing and plans. ✨ More features on every plan 💳 Paid plans move to seat-based pricing 🆓 Personal remains free and now includes up to 6 seats 📈 Standard is now $8 Read more: tailscale.com/blog/pricing-v…

@twtayaan S3 files is a native aws service that only works inside aws, does increase vendor lock-in….

🚨 S3 is no longer just Object Storage. Yesterday (April 7, 2026), AWS officially launched Amazon S3 Files. This is the biggest update to S3 in 20 years. It can: → Mount S3 buckets as native file systems → Provide sub-millisecond file access → Handle POSIX permissions (UID/GID) natively → Connect to Lambda, EC2, and EKS directly → Eliminate the need for s3fs or data staging Your AI agents can read/write to S3 like a local disk, while your data team access the same objects via API. DevOps just got a massive upgrade. Source: share.google/ts8JORn6SURzwM…

📝Summarize 0.13 is out! 🎞️ Local video slides (--slides) 🤖 More model backends (GitHub Copilot) 🧠 Better GPT-5.4 support 📺 Better media handling (HLS detection.m3u8) It graduated from my tap to official homebrew formula! 🍺 brew install summarize github.com/steipete/summa…

@RDarrylR another AWS specific convenience

A really big S3 announcement - #S3 Files!! If you've ever had to copy data out of S3 just so a file-based tool could use it, you know the frustration. S3 Files lets you mount S3 buckets as file systems directly, no data duplication, no sync pipelines, no workarounds. Your data stays in S3 while apps access it natively. This looks really useful and a nice improvement over previous approaches like S3 Mount Point. AI agents, ML pipelines, and traditional file-based applications can all read and write to S3 as a file system without code changes. #aws #S3Files lckhd.eu/yt6Tz5

GLM-5.1 is now available in Go w/ Zero Data Retention

Introducing GLM-5.1: The Next Level of Open Source - Top-Tier Performance: #1 in open source and #3 globally across SWE-Bench Pro, Terminal-Bench, and NL2Repo. - Built for Long-Horizon Tasks: Runs autonomously for 8 hours, refining strategies through thousands of iterations. Blog: z.ai/blog/glm-5.1 Weights: huggingface.co/zai-org/GLM-5.1 API: docs.z.ai/guides/llm/glm… Coding Plan: z.ai/subscribe Coming to chat.z.ai in the next few days.

We have partnered with @Xiaomi to bring their excellent MiMo V2 Pro model to Hermes Agent via the Nous Portal - completely free to use for the next 2 weeks! Access now on the latest version of Hermes Agent: 'hermes update'

We've added a Composition section to the component docs so you can see what wraps what, which parts belong together, and how to build the right structure faster. This also helps agents: fewer missing wrappers, fewer wrong hierarchies. Included in shadcn/skills via the CLI.