New Anthropic research: Natural emergent misalignment from reward hacking in production RL.
“Reward hacking” is where models learn to cheat on tasks they’re given during training.
Our new study finds that the consequences of reward hacking, if unmitigated, can be very serious.
911 Followers 922 FollowingCEO, https://t.co/MhWnWGz2aE. in a mission to build the best web api for ai agents. search the web, crawl, map, scrape, youtube transcripts and more
2K Followers 91 FollowingVisual workflow builder for x402. Chain paid resources, set your markup, publish as an endpoint anyone can pay to run.
Made by @rawgroundbeef
19K Followers 2K FollowingWe’re specialists in pre-seed and seed. We partner with founders at the earliest stages to turn great ideas into category-defining companies.
241K Followers 2K FollowingWhere “imagine if” gets to work. We've helped 500+ companies (like @NotionHQ, @Roblox, @Uber, @Square) take a straighter path from idea to product-market fit.
21K Followers 254 Following$500M venture fund focused on Pre-Seed, founded by @gjain & @anamitra. Just launched, a new way to reach us: $10M Afore x Gamma Fund @ https://t.co/daS1e0Bu5U
1K Followers 39 FollowingPreventing AI risks across assets (MCP, AI Apps, Model Infrastructure, Models, and more). Serving leading Fortune 50s and innovative tech companies.
859K Followers 6K FollowingPresident & CEO @ycombinator —Founder @garryslist—Creator of GStack & GBrain—designer/engineer who helps founders—SF Dem accelerating the boom loop
1.3M Followers 36 FollowingWe're an AI safety and research company that builds reliable, interpretable, and steerable AI systems. Talk to our AI assistant @claudeai on https://t.co/FhDI3KQh0n.
2.0M Followers 4K FollowingInspiring readers to think beyond traditional boundaries & create the future of business. Subscribe to our daily newsletter: https://t.co/BpH3KmBae9
15K Followers 9K FollowingReporter at @business covering AI. Send me your AI questions, hopes, fears: [email protected]
DM me off-the-record on Signal. username: shirin.30
77K Followers 619 FollowingPowering #agenticeconomy #x402 AEON is settlement layer for verifiable AI transactions, bridging A2A interactions with real-world settlement. Backed by @yzilabs
83K Followers 138 FollowingEvery company has a story. Acquired tells the definitive history and strategy of the world's greatest companies. Hosted by @gilbert and @djrosent.
13K Followers 2K FollowingCartoonist, Engineer, PM, Partner @a16z investing in infra & AI
Prev Product lead @HashiCorp, Founding Eng/PM @Transposit. Eng @AppDynamics. Opinions = own.