Short posts
Mitigating prompt injections by building a custom Python interpreter. Very cool research here. –> CaMeL offers a promising new direction for mitigating prompt injection attacks
Got v1 of my llm evals dashboard set up –> Article tracking: Trump | LLM evals - Kevin Schaul
“Finnish company Check First scoured Wikipedia and turned up nearly 2,000 hyperlinks on pages in 44 languages that pointed to 162 Pravda websites.” –> Russia seeds chatbots with lies. Any bad actor could game AI the same way.
Marimekko chart alert –> See why Trump’s reversal actually increased tariff rates
This is absolutely bonkers –> The Trump Administration Accidentally Texted Me Its War Plans
Props to nyt for keeping this public resource going –> https://www.nytimes.com/2025/03/17/polls/donald-trump-approval-poll-tracker.html
Looking forward to digging into this tutorial #NICAR25 –> Go big with GitHub Actions — Go big with GitHub Actions documentation