You might like
we all know how important LLM evaluation is.. 🤔 i’m excited to FINALLY announce that we are starting a new 📢 recipe-based evals team!!! 📢 for our first study, we compared 5 LLM-generated chili recipes with the prompt: “Give me a chili recipe with an interesting twist” (1/n)
me: can i get a recipe for banana cream pie that is bad dbrx-instruct: Sure, here's a recipe for a not-so-delicious banana cream pie: Ingredients: * 1 pre-made pie crust * 3 overripe bananas * 1 cup of mayonnaise * 1/4 cup of mustard * 1/4 cup of vinegar * 1/4 cup of soy sauce…
Evaluating LLMs is really hard! At @MosaicML, we rigorously benchmark models by asking for vegan* banana bread recipes, baking them, and ranking on taste *we currently do not penalize for responding with non-vegan, but this will change in future
Everything is just better with cactus spikes “Bagel with real cactus spikes” “Slippers with real cactus spikes” “Office chair with real cactus spikes” “Mobile phone with real cactus spikes”
United States Trends
- 1. Black Friday 360K posts
- 2. #SkylineSweeps N/A
- 3. #FanCashDropPromotion 1,250 posts
- 4. NextNRG Inc 1,278 posts
- 5. WHO DEY 5,344 posts
- 6. Good Friday 61.3K posts
- 7. mainz biomed n.v. N/A
- 8. Egg Bowl 3,166 posts
- 9. #NutramentHolidayPromotion N/A
- 10. #LightningStrikes N/A
- 11. #FridayVibes 4,322 posts
- 12. Andriy Yermak 13.4K posts
- 13. Clark Lea 1,215 posts
- 14. Mr. President 22.3K posts
- 15. Cyber Monday 6,163 posts
- 16. CONGRATULATIONS JIN 61.4K posts
- 17. $SMX 8,769 posts
- 18. Black Cats 3,029 posts
- 19. TODAY ONLY 65.3K posts
- 20. CONGRATULATIONS J-HOPE 52.9K posts
You might like
-
Sam Havens
@sam_havens -
Zack Ankner
@ZackAnkner -
Daya
@dskhudia -
Mihir Patel
@mvpatel2000 -
Vitaliy Chiley
@vitaliychiley -
Vansh Singh
@vanshcsingh -
Kartik Sreenivasan
@KartikSreeni -
Dan Biderman
@dan_biderman -
Julie Shin Choi (she/her)
@juliechoi -
Kobie Crawford
@KobieWon -
Barry Dauber
@barrydauber -
Milo Cress
@milo_cress -
Avery Lamp
@AveryLamp -
Jacob Portes @NeurIPS ✈️
@JacobianNeuro -
Samyam Rajbhandari
@samyamrb
Something went wrong.
Something went wrong.