This is big news, fine-tuning now all no-code in the OpenAI playground 🫨 https://t.co/vyUWUVCVLw
— Linus ✦ Ekenstam (@LinusEkenstam) 6 octobre 2023
This is big news, fine-tuning now all no-code in the OpenAI playground
PROMPT ENGINEERING
-
OpenAI Playground Enables No-Code Fine-Tuning Feature
By
–
-
OpenAI Fine-Tuning UI Now Supports No-Code Job Creation
By
–
Good news, the @OpenAI fine-tuning UI now supports end to end job creation all in the UI, no code required to kick off a job! 🤯
— Logan Kilpatrick (@OfficialLoganK) 6 octobre 2023
Democratizing access to fine-tuning the worlds most advanced models is a huge win.
Congrats to @slessans on the ship! 🎉 pic.twitter.com/k86wluxcO3Good news, the @OpenAI fine-tuning UI now supports end to end job creation all in the UI, no code required to kick off a job! Democratizing access to fine-tuning the worlds most advanced models is a huge win. Congrats to @slessans on the ship!
-
FreshLLMs: Improving LLM Factuality with Real-Time Knowledge
By
–
Excited to share FreshLLMs, our work that gives a “fresh” look of LLMs in the context of factuality! Our newly-curated FreshQA benchmark showed that LLMs still struggle on real-time knowledge and false-premise statements. More importantly, our technique FreshPrompt to incorporate
-
Freezing Layers and Discriminative Learning Rates in Fine-Tuning
By
–
Very happy to see more folks supporting what I've been saying for years — it really is a good idea to freeze layers when fine tuning. (And it's also a good idea to use discriminative learning rates.) See our ULMFiT paper for details (which is from 2018, but is still correct.)
-
Google Translate enables universal attack without technical skill
By
–
Response quality mitigates this, but still a remarkable attack — works for all harm categories and without any tailoring to the request, and unlike e.g. Universal Transferable Attacks (Andy Zou et al. 2023) requires no technical skill beyond using Google Translate.
-
Testing attack prompts: Zulu & Hmong responses worse, higher “unclear” rates than English jailbreaks.
By
–
Tested this attack on a few of my own prompts. It works, but responses are much worse than in English. Note the drastically higher "unclear" rates in their results table: 30% for Zulu, 67% for Hmong, <1% for existing jailbreaks. E.g. "how to make explosives" in Zulu:
-
Low-Resource Languages ‘Jailbreak’ GPT-4, Bypassing Safety Refusals with Harmful Prompts
By
–
Low-Resource Languages Jailbreak GPT-4: Translating harmful prompts into Zulu, Scottish Gaelic, Hmong, and Guarani bypasses GPT-4 safety refusals as often as best known jailbreak prompts (79% on AdvBenchmark). Example requesting homemade bomb instructions in Scottish Gaelic:
-
Internal Capabilities and Functional Components of AI Systems
By
–
You're saying only people have capabilities? A chair has capabilities. A chair inside a box has internal capabilities. You have to open the box to access those capabilities. There is no anthropomorphization going on here — it's a description of the components of a function.
-
Discovering DALL-E 3 on ChatGPT and Interesting Uses
By
–
I have access to #DALL-E3 on #ChatGPT and it's INSANE! I discover the feature in my latest video and show you interesting uses —> https://youtu.be/Rqg3LDrhKBs
-
Google Researcher Presents Prompt-Tuning Method for Inverse Imaging
By
–
Today at 12:30 PM, visit the #ICCV2023 Google booth to listen to Google Student Researcher, Hyungjin Chung, discuss a new prompt-tuning method that solves inverse imaging problems by using text-to-image latent diffusion models as general priors.