For clarity, I extended the base model — not the instruct version, so this is expected.
GENERATIVE AI
-
ChatGPT Hack: Dependency Grammar for Humanizing Text
By
–
ChatGPT Hack: Tired of AI generated content that sounds too much like ChatGPT? Use Dependency Grammar Framework in your prompts. It changes the output to sound 100% like a human. Follow the thread:
-
Adobe Firefly and AI Tools Dominate Tech News Today
By
–
Top stories in AI today: -Adobe reveals new Firefly model
-Apple makes another quiet AI acquisition
-Bring your sketches to life for free
-Sakana unveils Japanese image model
-6 new AI tools & 4 new AI jobs Read more: http://
therundown.ai/p/adobes-new-a
i-superpowers
… -
Custom GPTs Updated with Dependency Grammar Framework
By
–
I just updated my Custom GPTs with Dependency Grammar Framework! You can test them out, but I already see content output as 100% human written: – Sales Email Generator GPT: https://
godofprompt.ai/gpts/sales-ema
il-generator
… – SEO Article Generator GPT: https://
godofprompt.ai/gpts/seo-artic
le-writer
… – Article Rewriter GPT: -
Phi Training Approach Criticism: Quality Data vs Quantity Debate
By
–
in my opinion, the Phi approach to training language models is just wrong • i'm not convinced that training on less (albeit "higher-quality") data is better than training on as much data as possible
• i'm not convinced that training on synthetic data ever works better than -
Evaluating Speed Cost and Offline AI Performance Metrics
By
–
Speed, cost and the ability to run offline on a personal device are the things I care most about I still don't have a great answer for how to best evaluate these things but I'm researching that at the moment
-
NVIDIA Hopper leads generative AI performance in MLPerf benchmarks
By
–
NVIDIA Hopper takes lead in Generative AI on MLPerf! See https://
nvda.ws/3J1knIW In the latest (4th) round of #MLPerf performance benchmarking – the 'gold standard' for #AI workload #testing – the formidable Llama 2 70B and Stable Diffusion XL are center stage -
GPT-5, Gemini 2.0, and the race for LLM advancement
By
–
I see a lot of comments on how much is riding on GPT-5 to show LLMs haven’t plateaued (I have said similar). But it isn’t like OpenAI is the only company expecting future big model improvement. We know Gemini 2.0 is in the cards, and we know Anthropic & X are training new models.
-
GPT-3.5 prompt injection defense and fine-tuning advantages
By
–
I quite like that they're using GPT3.5 here – for prompt injection a defense that works with the less expensive, faster models would almost certainly work with the more expensive ones too I imagine GPT-3.5 is better for fine tuning at the moment because there's more experience