Keep on to blur preview images; turn off to show them clearly
bingo
intercomputer realist @a16zcrypto / editor https://t.co/fGE7XDfsKo / cofounder @FortuneCrypto
For more of Anthropic’s alignment research, see our Alignment Science blog: https://t.co/0UHuZdvWd9
We'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.
Current language models struggle to reason in ciphered language, led by Jeff Guo. Training or prompting LLMs to obfuscate their reasoning by encoding it using simple ciphers significantly reduces their reasoning performance.
For more of Anthropic’s alignment research, see our Alignment Science blog: https://t.co/0UHuZdvWd9
The Anthropic Fellows program provides funding and mentorship for a small cohort of AI safety researchers. Here are four exciting papers that our Fellows have recently released.
Stress-testing model specifications, led by Jifan Zhang. Generating thousands of scenarios that cause models to make difficult trade-offs helps to reveal their underlying preferences, and can help researchers iterate on model specifications.
RT @arcprize: ARC Prize 2025 - Submissions Closed! Thank you to the 1,495 teams that made 15,923 submissions Final results depend on open…
Co-founder @ndea. Co-founder @arcprize. Creator of Keras and ARC-AGI. Author of 'Deep Learning with Python'.
Fentanyl is among the greatest silent wars ever waged against the American people. Proud of those who are doing everything they can to stop it.
Co-Founder, American Dynamism. General Partner @a16z. Catholic. Mother. American. 🇺🇸 🚀💪
