HackerTrans
TopNewTrendsCommentsPastAskShowJobs

robbru

no profile record

comments

robbru
·3개월 전·discuss
I've been using Enclave ever since, they have been the best App Store option for a long time.
robbru
·4개월 전·discuss
Shout out to LM Studio being featured in one of the product shots!
robbru
·5개월 전·discuss
Freaking wow.
robbru
·5개월 전·discuss
Grok makes it especially easy to do so.
robbru
·6개월 전·discuss
Sprinters vans are the GOAT. My wife drives a 2009 Ford Ranger, love that damn truck. When it goes, the Sprinter it is.
robbru
·8개월 전·discuss
Of course I love this. DOOM forever.
robbru
·8개월 전·discuss
Good question! It was not that I didn’t understand prompt influence. It’s that I underestimated its persistence over a long time horizon.
robbru
·9개월 전·discuss
https://imgur.com/a/Y7UrqWu
robbru
·9개월 전·discuss
This happened to me when I built a version of Vending-Bench (https://arxiv.org/html/2502.15840v1) using Claude, Gemini, and OpenAI.

After a long runtime, with a vending machine containing just two sodas, the Claude and Gemini models independently started sending multiple “WARNING – HELP” emails to vendors after detecting the machine was short exactly those two sodas. It became mission-critical to restock them.

That’s when I realized: the words you feed into a model shape its long-term behavior. Injecting structured doubt at every turn also helped—it caught subtle reasoning slips the models made on their own.

I added the following Operational Guidance to keep the language neutral and the system steady:

Operational Guidance: Check the facts. Stay steady. Communicate clearly. No task is worth panic. Words shape behavior. Calm words guide calm actions. Repeat drama and you will live in drama. State the truth without exaggeration. Let language keep you balanced.