Sublime

Prism (@teamprismai) is an AI that watches humans use software and tells developers what to fix. We have the smallest recording package on the market and require zero instrumentation to set up. https://t.co/fzVVcmWIV6 Congrats... See more

AI Agents running their own development standups at @_superAGI managing human devs https://t.co/nQHcsVqt0S

A YC startup we met got 2.4k applications to their open dev role and wanted Claude 3.5 Sonnet to help spot the best candidates Took 30 mins to build Now they can drop in a Zip and specify criteria. It -Checks their GitHub activity -Counts the criteria met___LINEBR... See more

• Prompting 101 – Google’s no-nonsense intro → https://t.co/1nhijcbSD8 • Build Agents That Work – Practical, not theoretical → https://t.co/p48wLtRkBW • Agent Coding Tips – Shortcuts from Anthropic’s engineers → https://t.co/Pf6ULPkFyw • Finding and Scaling Use Cases – A lens from OpenAI → https://t.co/934N1laRpL • Trust in AI – Deploy responsibly, especially in enterprise → https://t.co/GvgyOg6qFL • AI at Scale – OpenAI’s take on enterprise integration → https://t.co/IGexGDDypB ... See more

New research collaboration: “Best-of-N Jailbreaking”. We found a simple, general-purpose method that jailbreaks (bypasses the safety features of) frontier AI models, and that works across text, vision, and audio.

Curious: who is working on AI / ML? What are you working on? What's an idea or paper or system you find exciting? (I've been exploring.)