-
perceiver-pytorch
Implementation of Perceiver, General Perception with Iterative Attention, in Pytorch
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
I think that's confusing between:
1. Accusations that AUTOMATIC1111 (the web frontend developer) copied code from the NovelAI leak relating to the loading of hypernetworks
2. Anlatan (company behind NovelAI) copying code from AUTOMATIC1111's repo, which does not have a permissive license, relating to the weighting of words
The third party MIT-licensed code is relevant to #1. Some code AUTOMATIC1111 was accused of copying from the leak (https://i.imgur.com/r1AkvBG.png) actually already appears in multiple older permissively-licensed public repos (https://github.com/lucidrains/perceiver-pytorch/blame/main/p..., https://github.com/CompVis/stable-diffusion/blob/main/ldm/mo...), one of which was credited in the readme by AUTOMATICC1111.
For #2, the Anlatan CEO blamed it on an intern (https://i.imgur.com/BFjKG1V.png). The leak shows that the offending code was committed by the CEO (https://i.imgur.com/aLiA2tr.png), which doesn't necessarily rule it out originating from an intern (e.g: "send me the code over teams to review and I'll add it") but doesn't look great.
From other examples I'd say AUTOMATIC1111 did get a bit sloppy in terms of not following clean-room design regarding the leak, but I'm inclined to give some leeway to a solo developer making a hugely popular public tool for free.
I think that's confusing between:
1. Accusations that AUTOMATIC1111 (the web frontend developer) copied code from the NovelAI leak relating to the loading of hypernetworks
2. Anlatan (company behind NovelAI) copying code from AUTOMATIC1111's repo, which does not have a permissive license, relating to the weighting of words
The third party MIT-licensed code is relevant to #1. Some code AUTOMATIC1111 was accused of copying from the leak (https://i.imgur.com/r1AkvBG.png) actually already appears in multiple older permissively-licensed public repos (https://github.com/lucidrains/perceiver-pytorch/blame/main/p..., https://github.com/CompVis/stable-diffusion/blob/main/ldm/mo...), one of which was credited in the readme by AUTOMATICC1111.
For #2, the Anlatan CEO blamed it on an intern (https://i.imgur.com/BFjKG1V.png). The leak shows that the offending code was committed by the CEO (https://i.imgur.com/aLiA2tr.png), which doesn't necessarily rule it out originating from an intern (e.g: "send me the code over teams to review and I'll add it") but doesn't look great.
From other examples I'd say AUTOMATIC1111 did get a bit sloppy in terms of not following clean-room design regarding the leak, but I'm inclined to give some leeway to a solo developer making a hugely popular public tool for free.
This story reminded me of the Public Apis Github repo situation. Similar scenario, as soon as it became under corporate control things got wonky.
Repo issue explaining the situation: https://github.com/public-apis/public-apis/issues/3104