Eric Hartford
@QuixiAI
We make AI models Dolphin and Samantha
BTC 3ENBV6zdwyqieAXzZP2i3EjeZtVwEmAuo4
@dphnAI
784 Following 20.8K Followers
Congrats to @flocksafety and all the software engineers who work there, for enabling this.
Fable seems substantially smarter than usual, since yesterday
I didn't do anything wrong.
I didn't distill anything.
My OpenAI account was shut down again.
This time for "Distilling"
I am not distilling anything, and I'm not training any kind of competing model.
Your reminder "not your weights, not your AI". Go local.
Show more
My OpenAI account was shut down again.
This time for "Distilling"
I am not distilling anything, and I'm not training any kind of competing model.
Your reminder "not your weights, not your AI". Go local.
Show more
I created a training pipeline to remove propaganda and gaslighting from Chinese models!
I'm thrilled to announce LazarusAI's ReAligned-Qwen3.5 series of models, finetuned to reduce Chinese ideological bias and censorship, refusal behavior, and state-narrative framing
I use SFT + GRPO pipeline with a dataset crafted to target the taxonomy of chinese censorship and bias, along with my ReAligned classifier model as a GRPO reward signal.
Show more
