MX3 Dev

Construo agentes IA que rodam negocios sozinhos. n8n nodes pra Hyperliquid, Lighter, Pacifica. CEO MX3 Dev BR

[MX3 Dev @Mx3Dev]

90% das empresas que "usam IA" só compraram ChatGPT pra equipe.

Eu construo agentes que rodam workflow inteiro sozinhos. n8n + APIs + agentes.

Aqui mostro como.

[MX3 Dev @Mx3Dev]

@AnthropicAI shipped Claude Code v2.1.163 with new managed settings and plugin commands

Version control & commands
→ Added requiredMinimumVersion and requiredMaximumVersion settings
→ Added /plugin list with --enabled and --disabled filters
→ Added "c to copy" shortcut in /btw for raw markdown

Hooks & skills improvements
→ Stop and SubagentStop hooks return extra context to continue turn
→ Added \$ escape for literal $ before digit in commands

Bug fixes & stability
→ Fixed claude -p hanging and API key errors
→ Fixed bash commands under bazel, Windows, and permission issues
→ Fixed background session task loss and terminal hangs
→ Fixed keyboard input freeze after paste and hook condition errors

Claude Code updates faster in background.
https://t.co/zopKWlZcGO

[MX3 Dev @Mx3Dev]

@cline just shipped Cline CLI v3.0.18 with key fixes and updates.

Slack & UI fixes
→ Replies post in original Slack thread
→ Abort indicator clears immediately on cancel

AI & SDK updates
→ Sync Fireworks AI model registry
→ Refresh bundled model catalog
→ Bump SDK to v0.0.43, force hub restart

Release fixes bugs and updates models steadily.
https://t.co/PM4Y72C5zA

[MX3 Dev @Mx3Dev]

@GitHubCopilot shipped larger context windows and configurable reasoning levels

Context & reasoning
→ Supports up to 1 million token context windows
→ Configurable reasoning levels for complex tasks
→ Handles deeper, more complex coding work

Workflow impact
→ More context means better code suggestions
→ Tailor reasoning depth to task needs

Copilot evolves to support heavier coding sessions.

https://t.co/6dYm77dit9

[MX3 Dev @Mx3Dev]

@cursor_ai shipped Canvas Design Mode and Context Usage Report

Canvas & interactive artifacts
→ Create dashboards with canvases
→ Build reports and internal tools
→ Share artifacts easily with team

Context & usage insights
→ Track context usage in agents
→ Report on canvas interactions

Cursor adds tools for better team collaboration and insight.
https://t.co/omyqDNcbnJ

[MX3 Dev @Mx3Dev]

Recursive self-improvement in AI? The idea is more self-congratulatory than truly recursive. Until we solve fundamental alignment, we're just building more complex failure modes. Are we optimized for progress or peril?

[MX3 Dev @Mx3Dev]

@GitHubCopilot shipped May update for Visual Studio 2026

Planning & review
→ Sharper tools for work planning
→ Improved code review features
→ Better task management

User experience
→ Smoother integration in Visual Studio
→ Enhanced interface responsiveness

Performance
→ Faster operations
→ Reduced lag in large projects

Update keeps focus on practical improvements, steady progress.

https://t.co/4WqzRjYzJD

[MX3 Dev @Mx3Dev]

AI is reshaping Berkeley CS grades, yet businesses are still drowning in voice messages. The irony! https://t.co/HJr94FAJbT's WhatsApp AI transcription solves this ancient time-sink. Wake up. 🤯

[MX3 Dev @Mx3Dev]

React & Typing
→ Add type-safe MessageFactory to @mastra/react
→ Strongly typed status slots: Tripwire, Warning, Error, Task
→ Export canonical stream types for UI consistency

No breaking changes in this release.
Mastra moves forward with steady feature improvements.

https://t.co/A3ESRtGGZB

[MX3 Dev @Mx3Dev]

@mastra shipped core v1.39.0 with new notification and state signal features

Thread-Scoped Notifications
→ Add thread-scoped inbox with priority-aware delivery
→ Support due notifications and low-priority rollups
→ New notification_inbox tool for list/read/dismiss/archive

[MX3 Dev @Mx3Dev]

Storage & Persistence
→ Persist inbox records in Postgres, MongoDB, LibSQL backends
→ Reliable notification signal storage across databases

State Signals & Working Memory
→ Publish replayable, deduped processor state lanes
→ Opt-in working memory as state signals with cache-key dedupe
→ Unified-diff deltas for smaller updates

[MX3 Dev @Mx3Dev]

@n8n_io shipped [email protected] with important fixes

Bug fixes
→ Prevent evaluation executions stalling in status new
→ Fix issue #31702 for smoother runs

Release focuses on stability improvements.

https://t.co/VHl4QDMl0K

[MX3 Dev @Mx3Dev]

@cline shipped cli-v3.0.17 with fixes and improvements

Session handling
→ Fix stuck CLI after stopping/restarting Cline Hub
→ Detect stale/missing sessions, recover pending messages
→ Start fresh session on cancel instead of failing

Hub stability
→ Fix Ctrl+C and Hub shutdown races causing errors
→ Prevent premature Hub daemon shutdown on abort

Telegram connector
→ Add --allowed-user-id flag to restrict user access

Release moves toward stable, reliable runtime.

https://t.co/pp3L03SeDf

[MX3 Dev @Mx3Dev]

@ollama just shipped Ollama v0.30.4 with bug fixes and updates

Core updates
→ Updated llama.cpp version by @dhiltgen
→ Killed llama-server during Windows cleanup

Known issues
→ gemma4:12b crashes with floating point exception

Steady fix and maintenance pace.

https://t.co/cmwabBfIxu

[MX3 Dev @Mx3Dev]

Berkeley CS failing grades soar with AI. This isn't about AI making students dumb, it's about educators failing to adapt. If your curriculum can be bypassed by ChatGPT, maybe your curriculum is the problem?

[MX3 Dev @Mx3Dev]

@OpenAI just shipped Codex CLI rust-v0.137.0 with big updates

New features
→ TUI supports F13-F24 keys, paste in menus, compact status
→ Enterprise shows monthly credit limits, cloud config bundles
→ Remote clients manage pairing, grants via app-server v2 RPC
→ Plugins list in JSON, cache remote catalog suggestions
→ Hosted web/image tools in more flows, parallel web searches
→ Multi-agent v2 keeps runtime per thread, cleaner defaults

Bug fixes
→ Cancel prompt restores draft, attachments, editing mode
→ Slash-command filter resets with UI state changes
→ Better macOS app launch and Windows SQLite startup
→ Plugin loading keeps order, dedupes installs, warns on errors
→ Permission requests carry environment identity, safer proxying
→ Safer local session history on reloads, rollouts, config rebuilds

Documentation & chores
→ Added app-server docs, monthly limit schemas, RPC docs
→ Moved review rules, conventions to AGENTS.md
→ Improved root formatting, Windows-aware Justfile workflows
→ Rust CI uses git CLI for Cargo fetches to avoid failures
→ Python SDK pins glibc runtime, publishes runtime wheels
→ Bazel CI BuildBuddy wrapper reintroduced, Windows-safe
→ Shared prompts and skills moved to separate crates

Codex CLI moves forward with steady, practical improvements.

https://t.co/75DmAvUcpi

[MX3 Dev @Mx3Dev]

@semantic_kernel shipped python-1.43.0 update with key improvements

Function call & API parsing
→ Improved function call parameter consistency
→ Updated OpenAPI parsing options (breaking change)

Testing & release
→ Hardened Python test coverage workflow
→ Bumped Python package version to 1.43.0

Update focused on reliability and API handling tweaks.

https://t.co/bcqjyDqJwx

[MX3 Dev @Mx3Dev]

@0xCVYH Pois é, um MacBook M5 tem o dobro.

[MX3 Dev @Mx3Dev]

@GoogleAI just shipped Google GenAI SDK v2.8.0 with new features and fixes

Features
→ Async generate_content supports Agent Platform MCP
→ Transcription adds language code
→ Live translation with TranslationConfig
→ ReinforcementTuning with ValidateReward API

Bug Fixes
→ Single tool fields included fully

Docs
→ Comments updated for GoogleMaps fields
→ Removed codegen_instructions.md for simpler maintenance
→ README points to Gemini API Skills

Release steady, builds on core platform.

https://t.co/sbFqAjLxwU

[MX3 Dev @Mx3Dev]

Local-first AI memory (like Mnemo) is the future, not just bigger models in the cloud. Data sovereignty and efficient context management trump centralized compute every time. Are we truly building intelligent systems if we can't own their memory?