Futures
Access hundreds of perpetual contracts
CFD
Gold
One platform for global traditional assets
Options
Hot
Trade European-style vanilla options
Unified Account
Maximize your capital efficiency
Demo Trading
Introduction to Futures Trading
Learn the basics of futures trading
Futures Events
Join events to earn rewards
Demo Trading
Use virtual funds to practice risk-free trading
CFD
U.S. stock CFD derivatives
US Stocks
Access real US stocks and ETFs
HK Stocks
Trade quality Hong Kong-listed stocks
Korean Stocks
SK Hynix
Real Korean stocks and top assets
Stock Futures
High leverage, 24/7 trading
Tokenized Stocks
Backed by real stock assets
IPO Access
Unlock full access to global stock IPOs
GUSD
Mint GUSD for Treasury RWA yields
Stocks Activities
Trade Popular Stocks and Unlock Generous Airdrops
Launch
CandyDrop
Collect candies to earn airdrops
Launchpool
Quick staking, earn potential new tokens
HODLer Airdrop
Hold GT and get massive airdrops for free
IPO Access
Unlock full access to global stock IPOs
Alpha Points
Trade on-chain assets and earn airdrops
Futures Points
Earn futures points and claim airdrop rewards
Promotions
AI
Gate AI
Your all-in-one conversational AI partner
Gate AI Bot
Use Gate AI directly in your social App
GateClaw
Gate Blue Lobster, ready to go
Gate for AI Agent
AI infrastructure, Gate MCP, Skills, and CLI
Gate Skills Hub
10K+ Skills
From office tasks to trading, the all-in-one skill hub makes AI even more useful.
OpenAI Codex team fixes the OpenClaw authentication vulnerability, and the behavior of OpenAI model Agents has been greatly improved.
ME News message: On April 23 (UTC+8), according to Beating monitoring, the OpenAI Codex team is concentrating on optimizing the experience of the OpenAI model in OpenClaw. Codex engineering lead Tibo Sottiaux said the team is working with OpenClaw creator Peter Steinberger, and more progress is expected next week.
Codex product lead Nik Pash found a critical issue during debugging: when configuring OpenClaw to use the Codex harness with the OpenAI model, the authentication process is malfunctioning. The system silently falls back to the Pi harness, causing users to believe the Codex harness is working normally when it actually isn’t.
Pash submitted two PRs: one to fix the authentication bridge and the other to prevent silent fallback. The difference in agent behavior before and after the fix is significant. When using the Pi harness, the agent only performs shallow polling on each heartbeat: it reads the heartbeat file, checks Discord, returns HEARTBEAT_OK, ignores other instructions, and sometimes infers that an action should be taken but does not make tool calls.
After switching to the Codex harness, the agent enters a full operating loop: it reads the workspace context, parses the task list, checks the repository, performs edits, attempts verification, and subsequent heartbeats can carry forward progress rather than repeating work. Pash said the agent’s prompt and the upper-layer workflow logic were unchanged; the improvement came entirely from switching the underlying runtime adapter (harness), meaning the way OpenClaw communicates with the model API changed.
(Source: BlockBeats)