github AutoGPT · just now · agents

AutoGPT platform beta v0.7.3 replaces email with Briefing system

from English

The AutoGPT team released version 0.7.3 of the autogpt-platform-beta, introducing a new notification architecture and several UI enhancements.

Replaces the existing email system with a Briefing/Alert/Verdict/Ops design.
Adds selectable ask_question options and Needs-You prompting rules to Copilot.
Displays live compaction progress within the Copilot chat interface.
Introduces expert team tools and polishes the copilot chat behind feature flags.
Commits to the new tool chain UX by dropping the previous experimental flag.
Fixes bugs related to expert delegation state, MCP OAuth popups, and user provisioning.

The update provides users with a more integrated notification experience and improved stability for team-based workflows.

Importance 1/3 Trust 2/3 AutoGPT AI agents Code generation

Read original

lab Claude Code Releases · 14h ago · 4 views

Claude Code v2.1.248 adds restricted mode and cross-session messaging

Claude Code v2.1.248 introduces a new `--restricted` mode that removes built-in command execution tools and ignores user settings to enhance security. The update also adds cross-session messaging capabilities between sessions on the same machine across Bedrock, Vertex, and Foundry environments.

media TLDR AI · 17h ago · 1 view

GLM-5.3 Flash approaches Claude Opus 4.8 on coding benchmarks

Z.ai revealed that the previously anonymously tested model ox-alpha is GLM-5.3-Flash, a 320B-parameter Mixture of Experts (MoE) model with 18B active parameters.

media Hugging Face Forums · 1d ago · 2 views

ZYR3 routes to 34 specialists with 1M context and local execution

ZYR3 is a multi-AI model that functions as an auto-router selecting from 34 specialist models based on task type, context, and token budget. It supports up to 1 million tokens of context and includes 14 language specialists along with an ULTRA Coding Prompt.

lab Claude Code Releases · 2d ago · 3 views

Claude Code v2.1.247 adds SendFeedback tool and cost optimization

Claude Code v2.1.247 introduces the new SendFeedback tool, allowing Claude to draft feedback reports for user review when issues arise. It also adds a /claude-api cost-optimize command to profile API spend and manage cost levers like caching and model choice.

lab NVIDIA Technical Blog · 2d ago · 4 views

Alibaba releases Qwen3.8-Flash-Next 176B preview weights for agentic coding

Alibaba has released the model weights for Qwen3.8-Flash-Next, serving as a preview of the upcoming Qwen4 architecture for developers to experiment with and evaluate.