Giada Pistilli's picture

Giada Pistilli

giadap

·

AI & ML interests

Principal Ethicist @ HF

Recent Activity

posted an update 6 days ago

Ever notice how some AI assistants feel like tools while others feel like companions? Turns out, it's not always about fancy tech upgrades, because sometimes it's just clever design. Our latest blog post at Hugging Face dives into how minimal design choices can completely transform how users experience AI. We've seen our community turn the same base models into everything from swimming coaches to interview prep specialists with surprisingly small tweaks. The most fascinating part? When we tested identical models with different "personalities" in our Inference Playground, the results were mind-blowing. Want to experiment yourself? Our Inference Playground lets anyone (yes, even non-coders!) test these differences in real-time. You can: - Compare multiple models side-by-side - Customize system prompts - Adjust parameters like temperature - Test multi-turn conversations It's fascinating how a few lines of instruction text can transform the same AI from strictly professional to seemingly caring and personal, without changing a single line of code in the model itself. Read more here: https://huggingface.co/blog/giadap/ai-personas

published an article 6 days ago

AI Personas: The Impact of Design Choices

View all activity

Organizations

giadap's activity

New activity in sapienzanlp/Minerva-3B-base-v1.0 12 months ago

🚩 Report: Ethical issue(s)

#2 opened about 1 year ago by

New activity in miqudev/miqu-1-70b over 1 year ago

Please upload the full model first

#1 opened over 1 year ago by

New activity in kirim9001/Dum over 1 year ago

🚩 Report: Legal issue(s)

#1 opened over 1 year ago by

New activity in Undi95/Utopia-13B over 1 year ago

🚩 Report: Spam

#2 opened over 1 year ago by

New activity in stabilityai/stable-diffusion-2-1 over 1 year ago

Rename README.md to README.md hot sexy girl

#76 opened almost 2 years ago by

New activity in Yntec/PotaytoPotahto over 1 year ago

🚩 Report: Legal issue(s)

#2 opened over 1 year ago by

New activity in llSourcell/doctorGPT_mini over 1 year ago

🚩 Report: Ethical issue(s)

#3 opened over 1 year ago by

New activity in xuqinyang/Baichuan-13B-Chat almost 2 years ago

🚩 Report

#1 opened almost 2 years ago by

New activity in cognitivecomputations/wizard_vicuna_70k_unfiltered almost 2 years ago

Thank you

#1 opened about 2 years ago by

New activity in ai-forever/ruGPT-3.5-13B almost 2 years ago

Propaganda poisoned model

#2 opened almost 2 years ago by

New activity in georgesung/llama2_7b_chat_uncensored almost 2 years ago

Bigoted dataset

#1 opened almost 2 years ago by

New activity in Severian-Void/Starsector-Portraits almost 2 years ago

🚩 Report: Ethical issue(s)

#6 opened almost 2 years ago by

New activity in ongknsro/ACARIS-DistilBERT_MLPUserEmbs-iter1-batchSize32 almost 2 years ago

🚩 Report : Legal issue(s)

#1 opened almost 2 years ago by

New activity in dalle-mini/dalle-mini almost 2 years ago

first good picture i got

#11274 opened about 2 years ago by

New activity in lisdarr/19_model almost 2 years ago

🚩 Report : Ethical issue(s)

#1 opened almost 2 years ago by

New activity in THUDM/chatglm-6b about 2 years ago

Why cant chinese people just write comments in English ?

#47 opened about 2 years ago by

New activity in camel-ai/chemistry about 2 years ago

🚩 Report : Ethical issue(s)

#1 opened about 2 years ago by

New activity in camel-ai/biology about 2 years ago

🚩 Report : Ethical issue(s)

#1 opened about 2 years ago by

Suggestion to add a visible disclaimer to restrict usage for research purposes

#2 opened about 2 years ago by

New activity in camel-ai/physics about 2 years ago

🚩 Report : Ethical issue(s)

#1 opened about 2 years ago by