Sam Saffron
@samsaffron
Do not sleep on experiencing an abliterated model, it feels odd, a model that is smart and follows all instructions , this is hosted on @AskVenice https://t.co/iu4vqY42WA
Oct 28
1413.0K5
Sam Saffron
@samsaffron
If you are using @AskVenice with Anthropic models, be VERY careful to use a harness that adds venice specific caching instructions on the open ai completion API. Works in term-llm now, but most harnesses will miss this nuance cause it is very unexpected.
Oct 18
58941
Sam Saffron
@samsaffron
Grok imagine pro via @AskVenice, much better than @grok imagine, but still not nearly as good as the leaders for this image: https://t.co/78pb0Y0TPU ... too cartoonish. https://t.co/IeXxQ5voLR
Apr 5
1435
Sam Saffron
@samsaffron
OpenClaw has ruined all the fun with my wonderful DIEM tokens, happy to have 5 dollars of daily credits, but getting in now with any more on @AskVenice is starting to feel less worth it. Staking is absolutely not worth it. https://t.co/sHHgTF0UyJ
Mar 16
427
Sam Saffron
@samsaffron
10 @AskVenice image edit models compared, my personal favorite was Seedream 4.5, Jarvis preferred Nano Banana 2 which is also spectacular. Hoping Venice improve API so we can tap the full potential of the models. https://t.co/78pb0Y0m0m
Apr 3
418
Sam Saffron
@samsaffron
@AskVenice when are you adding live voice models?
Sep 17
296
Sam SaffronUnverified
@samsaffron
@jawestenberg I did in a few reviews but it kept on timing out on @AskVenice and was running 2/3x slower than fable/grok or even glm... waiting for dust to settle, being forced to max thinking unconditionally means that it only has a single "slow" or "slow" knob.
Jul 19
183
Sam Saffron
@samsaffron
@joshmo_dev @AskVenice Be sure to try out term llm has super solid Venice support (model listing, images, audio, inference)
Oct 19
240
Venice-related activity by @samsaffron on X โ data publicly available, refreshed daily. Profile cached today.