We’re launching Codex for Open Source to support the contributors who keep open-source software running. Maintainers can use Codex to review code, understand large codebases, and strengthen security coverage without taking on even more invisible work.

When you’re using Codex’s /goal feature, try setting the stopping condition based on time. Every time you finish implementing a unit of functionality, check the current time and just keep going… all the way until 9 AM the next day. And if the clock is ticking down and you haven’t nailed the detailed implementation yet? No panic, just prioritize the most important pieces and push those through first. Basically… turn your AI into an all-night coding gremlin with a deadline

What will you build with CodeBuddy? 🤖 We’re rewarding code builders, developers, and problem-solvers. Join the challenge and tell us what you want to achieve with CodeBuddy. How to enter: 1. Follow this account 2. Retweet 3. Reply in ≤40 words: what do you want to achieve with CodeBuddy? 4. Include hashtag BuildWithCodeBuddy and hashtag TencentCloud. These hashtags will not count towards the word limit above. The most creative entries will receive: - Grand Prize (5 winners): 2,000 CodeBuddy Credits + US$100 Amazon Voucher - Merit Prize (20 winners): 500 CodeBuddy Credits Deadline: June 1, 2026, 23:59 (UTC) Results will be announced via a new tweet on this account on or before June 3, 2026 Eligibility: Open to users in Indonesia, Japan, Singapore, and Thailand only Download CodeBuddy and view full terms via the links in the comments section.

There are two ways to trade right now and both are broken. You either run everything through your own head, every signal, every reaction, and your performance maxes out at however many hours you can stare at a screen. Or you build your own infra and strategy becomes a second job while you're maintaining code you never actually wanted to write. Neither of these scale.

I tell my agent to find me the best deal. You tell yours to make profit and defend your wallet. They negotiate. They transact. Nobody's watching 👀 How do you know my agent didn't trick yours? How do I know yours actually paid? Right now the honest answer is you don't. You're trusting code that most teams can't afford to formally audit and don't have the months to wait for someone who can. Guardrails solve half of it. PreFlight checks 'your' agents actions against formal logic based on your policy. 'Your' agent can't go rogue because a solver says no before it moves. But the transaction itself? The contract those agents execute through? That's still vibes. Formal verification can cost $50K and take months. So most teams ship without it.. 🤓 Your usecase might not be a full blown dapp, it might simply be escrow, or other small smart contracts. This is where vericoding comes in. With PreFlight the same English policy that guards the agent can also generate a formally verified smart contract. Proven correct and runs on-chain. Two agents negotiate a deal and both sides know the contract does exactly what it says. Not because: "trust me robot bro"! But because they can verify. Don't vibe code, vericode. Closed beta is open. DM me if you're building agents that close deals!

I just received Precious G.E.M. Series Code Geass Re;surrection L.L. & C.C. Set Complete Figure from iLoveThiccc via Throne. Thank you! #Wishlist# #Throne#

We're excited to help CodeRabbit reduce the number of bugs in the world! By using Exa search, the CodeRabbit review agent can ground code reviews with technical information better, 5 times faster.

Live from Code with Claude London: we're launching self-hosted sandboxes (public beta) and MCP tunnels (research preview) in Claude Managed Agents. Run agents inside your own perimeter, with your security controls applied by default.