Gate News message, April 23 — The OpenAI Codex team is focused on optimizing the OpenAI model experience in OpenClaw, with Codex engineering lead Tibo Sottiaux collaborating with OpenClaw creator Peter Steinberger. Codex product lead Nik Pash discovered a critical authentication flaw: when OpenClaw was configured to use Codex harness with OpenAI models, the authentication process failed and the system silently fell back to Pi harness, causing users to believe Codex harness was functioning normally when it was not.
Pash submitted two pull requests to address the issue: one to fix the authentication bridge and another to prevent silent fallback. The improvements stem entirely from switching the underlying runtime adapter (harness) that governs how OpenClaw communicates with the model API, while the agent’s prompt and higher-level workflow logic remained unchanged.
Agent behavior showed marked differences before and after the fix. With Pi harness, the agent performed shallow polling on each heartbeat: reading heartbeat files, checking Discord, returning HEARTBEAT_OK, and ignoring other instructions. It sometimes inferred operations to execute but failed to issue tool calls. After switching to Codex harness, the agent entered a full work loop: reading workspace context, parsing task lists, checking repositories, executing edits, and attempting verification. Subsequent heartbeats could resume progress rather than repeat work.
Disclaimer: The information on this page may come from third parties and does not represent the views or opinions of Gate. The content displayed on this page is for reference only and does not constitute any financial, investment, or legal advice. Gate does not guarantee the accuracy or completeness of the information and shall not be liable for any losses arising from the use of this information. Virtual asset investments carry high risks and are subject to significant price volatility. You may lose all of your invested principal. Please fully understand the relevant risks and make prudent decisions based on your own financial situation and risk tolerance. For details, please refer to
Disclaimer.
Related Articles
Google CEO: Capital expenditures in 2026 will reach $185 billion; ramping up investment in the era of AI agents
Google CEO Sundar Pichai announced at Google Cloud Next in Las Vegas on April 22 that Google plans to invest $175 billion to $185 billion in 2026 in capital expenditures to build the infrastructure needed for autonomous AI agents, up from $31 billion in 2022.
MarketWhisper33m ago
Google Jules releases a new version candidate list, repositioning it as an end-to-end product development platform
According to the official April 23 announcement by the Google Jules team, Jules’s product positioning has been upgraded from an asynchronous coding agent to an “end-to-end agentic product development platform.” The new version can read the full product context, independently determine the next steps for building, and submit a PR. The official also announced that the new version candidate list is now open.
MarketWhisper39m ago
Google Jules Rebrands as End-to-End Agentic Product Development Platform, Opens Waitlist for New Version
Gate News message, April 23 — Google's Jules team announced the opening of a waitlist for a new version of the product, repositioning Jules from an asynchronous coding agent to an end-to-end agentic product development platform. According to the official description, the upgraded platform reads enti
GateNews1h ago
Perplexity Discloses Web Search Agent Post-Training Method; Qwen3.5-Based Model Outperforms GPT-5.4 on Accuracy and Cost
Perplexity uses SFT followed by RL with Qwen3.5 models, leveraging a multi-hop QA dataset and rubric checks to boost search accuracy and efficiency, achieving best-in-class FRAMES performance.
Abstract: Perplexity's post-training workflow for web-search agents combines supervised fine-tuning (SFT) to enforce instruction-following and language consistency with online reinforcement learning (RL) via the GRPO algorithm. The RL stage uses a proprietary multi-hop verifiable QA dataset and rubric-based conversational data to prevent SFT drift, with reward gating and within-group efficiency penalties. Evaluation shows Qwen3.5-397B-SFT-RL achieving top FRAMES performance, 57.3% accuracy with a single tool call and 73.9% with four calls at $0.02 per query, outperforming GPT-5.4 and Claude Sonnet 4.6 on these metrics. Pricing is API-based and excludes caching.
GateNews1h ago
OpenAI Introduces ChatGPT Workspace Agents: Codex-Powered, Team Shared, Slack Integration
OpenAI launched Workspace Agents on April 22 in ChatGPT Business/Enterprise/Edu/Teachers, powered by Codex, designed for long-running cloud operation, shared by teams, and capable of offline execution. They can proactively respond in Slack and generate invoices, execute multi-step workflows, and support scheduling. The research preview is free until May 6; afterward, it will use a credit-based pricing model, with rates to be announced. They compete alongside Google Gemini Enterprise Agent Platform and Anthropic Claude Cowork. All three focus on enterprise-grade agents, but their positioning differs.
ChainNewsAbmedia3h ago
Google Cloud Next 2026: Launches Gemini Enterprise Agent Platform, $750 million to Help Consultants Deploy
Google Cloud unveiled the Gemini Enterprise Agent Platform at Cloud Next 2026, integrating model selection, agent building, DevOps, orchestration, and enterprise security controls, and launched a $750 million fund to help McKinsey, Accenture, and Deloitte deploy enterprise agents. The platform, along with Ironwood TPU, A2A, and MCP, builds its own full-stack offering and consulting channel, to counter OpenAI Operator and Anthropic Claude Enterprise.
ChainNewsAbmedia3h ago
