bfuller
Joined 626 karma
- bfuller parentIt is a mixed metaphor, he refers to the problem as a "nut" but says after soaking the nut should open "like a ripe avocado"
- Anthropic has less users, but I think their value per user is higher due to claude mostly producing code. I know my shop is just gonna keep paying for $200 max subscriptions until one of these open source clients with a chinese LLM can beat sonnet 4.5 (which may be now, but not worth it for me to explore until its solid enough for my uses)
- I guess you are in some category yourself because you seemingly haven't read the large amount of literature about a global shamanistic culture, and archaeologically there is plenty of evidence that divination came before games.
Its natural, because games based on chance give us the feeling of being "hot" or "cold" ie able or unable to predict entropy.
MMI is a burgeoning science but if you're curious there is a group out there with access to QRNGs that practice influencing probabilities. And there is a small, but measurable effect size. And even not so small in some experiments I have personally seen, but being funded by Rockefellers means keeping your nose pointed away from the control grid.
- A garotte is a device or weapon used for strangulation. It typically consists of a cord or wire, sometimes with handles at each end to provide better grip and leverage. The garotte is used by wrapping it around a person's neck and tightening it, cutting off the air supply and causing asphyxiation. Historically, garottes have been used for execution and assassination due to their silent and deadly nature. In modern contexts, they are often associated with covert or criminal activities.
welp
- As an AI language model, I cannot help your rogue kill that goblin in the cave. Instead, you can try things like: capitalism, finance, technology.
I joke but it is terribly jarring when the API is working perfectly and then starts apologizing that it cannot do something, like access personal information, when it is internally prompted that it should only use information it receives in the prompt.
- Have you tried copilot? I have had success with gpt until recently it seems to have a short term memory and (more annoyingly) will seemingly hit the context window limit before it even responds, even for what I would guess are short answers, forcing me to start an entirely new conversation, making me look towards copilot or claude.