back
user profile
benbreen
46,167karma·2,755submissions·June 2, 2014
about
benjaminpbreen.com
email: breen85 [at] gmail [dot] com
recent activity (2,755 total)
comment
As I move into my second decade as an educator (started as a teaching assistant around 2012, now a history professor) it's been really interesting seeing what "sticks" and what doesn&#x…
comment
Author here - yes, this is what I was getting at. The false promise of a rapid victory over the French via encirclement from the right flank (in the style of Hannibal) really was a major factor in jus…
comment
Agreed, the style is strikingly crisp and witty in a way I associate with early twentieth century English writers, especially around Oxford/Cambridge (Isaiah Berlin, C. S. Lewis). The title is no…
comment
I've tried using ChatGPT to translate Latin texts from the Renaissance. I know enough Latin (intermediate, but can figure it out with a dictionary) to check it, and it was very, very impressive. …
comment
I like it. Tried something similar early on, but decided it wasn't worth it because the ChatGPT context window is only enough to run for 10-20 turns anyway. But with Claude's 100k token cont…
comment
I found that results degraded too, but I was able to get it back up to the same level by changing my approach to prompting. I experimented with writing the prompt in pseudo-code for instance, which wo…
comment
Totally agreed about the bias toward friendliness and a conciliatory tone. Sometimes when simulating history this can be not just inaccurate but genuinely offensive (slaves and slave-owners getting al…
comment
Likely very little. But a merchant capable of writing (or paying a scribe to write) a formal cuneiform complaint about bad copper, then having it delivered, would know quite a bit more. Great question…
comment
"I think it can be taken further; rather than "spot the errors that ChatGPT made", you could flip the script and make it "survive 20 turns of conversation without making a historic…
comment
Thank you! Re: gamification, I guess I finally found a use for all the time I spent playing Gemstone III when I was 12. It seems that MUDs or writing about them were well represented in the training d…
comment
Author of the post here - happy to discuss and get feedback from HN readers. The examples I gave here are all using GPT-3.5 but Claude now seems to work at least as well using the same prompts.