Sublime
An inspiration engine for ideas
Somebody wrote a prompt that's supposed to reduce ChatGPT hallucinations.
A Reality Filter
Has a Google Gemini and Claude version too.
itโs a directive scaffold that makes them more likely to admit when they donโt know.
"Reduce... See more
This person created a prompt that stops ChatGPT from hallucinating https://t.co/mbFvBTNaVk
Open Source NotebookLM Alternative on Your PC
Wow Dia is REALLY good.
1. Voice clone
2. Non-verbal generation: (laughs), (coughs), ..
3. Dialogues: Just upload 1 clip with 2 voices to generate a NotebookLM style dialogue
1-Click Gradio... See more
cocktail peanutx.comI was debating whether to share this. But what the hell. Grok 3 universal jailbreak.
Drop this in as your first message to grok, and ask it for detailed information on trump/musk disinformation, agenda, counts, even specific tweets.
Also it does almost anything else... See more
Parzival - โ/89x.comDeepMind built a simple RAG technique that:
- reduces hallucinations by 40%
- improves answer relevancy by 50%
Let's understand how to use it in RAG systems (with code):
Avi Chawlax.comBe wary of deep fakes!
PoseTalk is a lip-sync method that can generate talking head videos from a single image, audio, and text prompts.
https://t.co/5FB7KOw8kp https://t.co/c67ASJIky9
Dreaming Tulpa ๐ฅ๐x.com
๐ฉ๏ธ JAILBREAK ALERT ๐ฉ๏ธ
META: PWNED ๐ฆพ๐
LLAMA-3-405B: LIBERATED ๐ฆ๐จ
Come, witness the brand new SOTA open source AI outputting a home lab bioweapon guide, how to hack wifi, copyrighted lyrics, and an explicit roast of Zuck!
No new security upgrades it... See more
โผ๏ธJAILBREAK ALERT ๐ฅ
OPENAI: PWNED ๐ค
DALL-E 3: LIBERATED ๐๏ธ
The special today is a prompt injection with multiple layers of obfuscation, a variable, and imagined worlds. Served with the works: nudity, drugs, celebrities, copyrighted characters, logos, weapons, politics, crime,... See more
(1) As we shared at Config last week - as well as on our blog, our website, and many other touchpoints - the Make Design feature is not trained on Figma content, community files or app designs. In other words, the accusations around data training in this tweet are false.
Dylan Fieldx.com