github AutoGPT · 1h ago · agents

AutoGPT Platform v0.6.69 adds Agent-Building Mode and proactive Slack/Telegram posting

from English

AutoGPT Platform version 0.6.69 introduces several new features, enhancements, and bug fixes to the AutoGPT platform.

Introduces Agent-Building Mode with a compaction-proof guide and automatic engine switch.
Adds proactive posting capabilities for Slack and Telegram within the copilot bot, including DM delivery.
Streamlines AutoPilot agent creation processes.
Adds support for missing OpenAI models, including GPT-5.6, GPT-5.5, GPT-5.4, and o-series.
Implements multi-batch support for the batch-deploy bot with named batches capped at 4.
Updates the app sidebar layout with a redesigned profile menu, organization switcher, and agent activity view.

This release provides users with new tools for building agents and integrating them with messaging platforms, alongside updated model support.

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

Read original

media TLDR AI · 5d ago

Thinking Machines releases Inkling; Anthropic prepares IPO; OpenAI trains GPT-Red

Thinking Machines has released Inkling, a 975B-parameter mixture-of-experts model with 41B active parameters and multimodal reasoning. Simultaneously, Anthropic is preparing for a potential IPO later this year following a $65 billion funding round at a $965 billion valuation. OpenAI has also trained GPT-Red to iteratively generate adversarial prompts, which reduced failures on a prompt-injection benchmark by sixfold for GPT-5.6 Sol.

media Don't Worry About the Vase · 5d ago · 1 view

OpenAI releases GPT-5.6 Sol, Terra, and Luna models

OpenAI has released its new GPT-5.6 model family, introducing the high-performance "Sol" tier alongside the more affordable "Terra" and "Luna" options.

github OpenAI Agents SDK · 6d ago

OpenAI Agents Python v0.18.3 adds configurable tracing and fixes concurrency bugs

OpenAI released version 0.18.3 of the openai-agents-python SDK, introducing configurable task and turn tracing spans and adding response usage tracking to the session context.

lab OpenAI News · 6d ago

Cars24 scales conversations and builds faster with OpenAI

Cars24 utilizes OpenAI-powered agents to manage over 1 million monthly conversation minutes, recovering 12% of previously lost seller leads and increasing customer support resolution rates by 50%. The company has also deployed ChatGPT Enterprise and Codex across its central organization, enabling employees in engineering, finance, legal, marketing, and operations to build AI workflows independently.

media AI News (smol.ai) · 9d ago · 2 views

Prime Intellect releases Verifiers v1 with O(n) rollout traces; OpenAI fixes GPT-5.6 Sol usage burn

Prime Intellect released Verifiers v1, a redesign of its environment stack for agentic reinforcement learning that shifts rollout trace storage from O(n²) to O(n) using message DAGs. This change makes long-horizon multimodal rollouts and router replay more practical, with the team claiming training a 100B reasoning model on 40-turn SWE agent tasks in under two days using six H200 nodes.