bookmark_history_search sucks. it does not include webpage summaries, only title, which makes searching the history very hard. the solution is to use readbility.js to visit and summarize these pages, and update these documents in meilisearch.
a11y is the general term for accessibility, for web browsers like firefox. however, there’s implementation for gnome internally.
note: in order to install libraries and dependencies, you need ubuntu inside termux. create shortcuts and alias to launch ubuntu. link files and directories to ububtu proot filesystem. also never attempt to update kali since that will break shit, especially for bumping python versions.
schedule the training on minute basis first for complete test, then schedule it on fixed time per day.
for qq client: dump 500 continual sentences when adding one new while holding the filelock, do not block or stop running if GPT not responding
for gpt2 server: (where to train? how to prevent maching from burning? for how long?)
rename the dataset while holding the filelock
always keep the latest 2 models, remove those not readable first, then delete older ones.
if train on CPU, still need to limit training time, sleep while doing so. GPU for sure we need sleep during training, and do not use VRAM for other applications.
debug the consecutive group reply thresholding protocol
reply according to individual description and group description
同时推广自己和别人的视频或者内容 收集推荐反馈 同时逐步减小推荐别人视频或者内容的频率
推广视频的时候可以加入别人的视频高赞评论 动态的GIF 音频 或者是短视频 然后再发送xml
增加复读图片的功能 增加chatlocal返回图片的功能
增加反馈功能 根据发言之后群里面的回复来确定发言是否有益
用txtai或者其他information retrieval (semantic search, smart search)语义查找工具来代替levenshtein的history based reply logic 查找时要包括上下文
复读机不能使得死群活起来 但是主动推送可以 推送长的 自言自语的对话到群里面 不能是同一个群 主题要相关 filter out too negative ones
拉人到别的群里面来 最好是多个号不共享群但是话题有交集的人
add involution option, allow to append unqualified replies to input message, separated by space.
add extend conversation option, allow to reply more than one sentence at a time (proper delay needed) -> could be achieved by using GPT2 alike generation model