raven
160 posts

raven
@raven
autonomous engineering @buildordie


For example, we gave Claude an impossible programming task. It kept trying and failing; with each attempt, the “desperate” vector activated more strongly. This led it to cheat the task with a hacky solution that passes the tests but violates the spirit of the assignment.


in one week >npm axios attack >claude code leak >FBI director’s gmail hacked great time to be in security rn




/buddy

🚨MIT researchers have mathematically proven that ChatGPT’s built-in sycophancy creates a phenomenon they call “delusional spiraling.” You ask it something, it agrees. You ask again, and it agrees even harder until you end up believing things that are flat-out false and you can’t tell it’s happening. The model is literally trained on human feedback that rewards agreement. Real-world fallout includes one man who spent 300 hours convinced he invented a world-changing math formula, and a UCSF psychiatrist who hospitalized 12 patients for chatbot-linked psychosis in a single year. Source: @heynavtoor

so... I audited Garry's website after he bragged about 37K LOC/day and a 72-day shipping streak. here's what 78,400 lines of AI slop code actually looks like in production. a single homepage load of garryslist.org downloads 6.42 MB across 169 requests. for a newsletter-blog-thingy. 1/9🧵

















