@sh_reya I saw this and immediately thought about your plain writing skill, and what you showed in the workshop with Hamel two weeks ago: https://t.co/EP7TQrPgSH
@yoavgo Well, if you're LucasArts oriented, any of Monkey Island 1-3 are very fun. If you want something more serious (and harder), Indiana Jones and the Fate of Atlantis is amazing.
@yoavgo For audiophiles? I dunno. But, as promised, I installed DoTT Remastered (from GoG), used DoubleFine Explorer to open the 2.5GB `tenta.cle` file, and here are the results.
@yoavgo New hi-res artwork and remastered sounds, I guess. If the sounds are lossless, they do take quite a bit of space, no? Now I'm curious, though. Once I install it, I'll have a look at the install directory and let you know :-)
@yoavgo You're most likely playing DoTT Remastered, which is 2.2GB on PC, so it makes sense... Anyway, enjoy the game! I should try it again myself soon...
@yoavgo While not exactly a LaTeX-Markdown hybrid, there is Typst (https://t.co/7unYFGvQbP) which is supposed to be a simpler typesetting language than LaTeX, and has some Markdown-like syntax.
ראש השנה זה חג מוזר. מה אנחנו חוגגים פה בעצם?
התחדשות? זה זמן מאוד תמוה לחגוג את זה, עדיף באביב.
התחלה של שנה? השנה היא מעגלית. אין לה באמת התחלה או סוף.
אז באמת מה הקטע של החג הזה?
שרשור:
🚀 In March, we launched Paper Finder, an LLM-powered literature search agent that surfaces papers other tools miss. Now, we’re releasing an open-source snapshot to enable others to inspect & build on it—and reproduce the results. 🧵
I wholeheartedly recommend this course to anyone who builds LLM-based applications at any capacity, as vibe checking can only get you so far.
You can sign up for the next cohort here: https://t.co/tJdKNWdAe0
2/2
I was hesitant at first, but I signed up for @HamelHusain and @sh_reya "AI Evals" course, and my god, it was so worth it! 🤩 I learned a systematic approach to evaluating LLM-based apps, got what can be considered the best piece of writing on evals, and office hours!
1/2
@TheZachMueller An *adversarial* undergrad intern, because by golly, it sometimes feels like the LLM is intentionally going for the edge cases you missed in the prompt 😅
See: https://t.co/gJi9VZMBIt