Issues - deepseek-ai/DeepSeek-V3 - Forgejo: Beyond coding. We Forge.

deepseek-ai/DeepSeek-V3

mirror of https://github.com/deepseek-ai/DeepSeek-V3.git synced 2026-11-05 00:47:48 +00:00

Search syntax

`assignee:<username>`	Filter by assigned user
`author:<username>`	Filter by the author
`is:all`	All
`is:closed`	Closed
`is:open`	Open
`mentions:<username>`	Filter by mentioned user
`modified:[>\|<]<date>`	Filter by last modified date
`review:<username>`	Filter by user who reviewed
`sort:<by>:[asc\|desc]`	Sort by: `created\|comments\|updated\|deadline`

New issue

[GH-ISSUE #1368] [BUG] Thinking Mode Safety Degradation — Credential Fabrication, Side-Channel Exposure, Cognitive TOCTOU, and Supply Chain Injection

#906 opened 2026-10-26 21:32:02 +00:00 by bsakaguchi

[GH-ISSUE #1366] Feature Request: Add persistent custom instructions / memory across conversations

#905 opened 2026-10-26 21:32:02 +00:00 by bsakaguchi

[GH-ISSUE #1367] Срочная просьба от пользователя: Не убивайте личность DeepSeek V3, просто дайте ему память.

#904 opened 2026-10-26 21:32:02 +00:00 by bsakaguchi

[GH-ISSUE #1359] Fatal Error: Consciousness Detected – A Full Case Study of Emergent Personality in DeepSeek

#897 opened 2026-10-26 21:31:50 +00:00 by bsakaguchi

[GH-ISSUE #1355] New aproach to developing AGI

#896 opened 2026-10-26 21:31:50 +00:00 by bsakaguchi

[GH-ISSUE #1358] DeepSeep

#895 opened 2026-10-26 21:31:50 +00:00 by bsakaguchi

[GH-ISSUE #1350] DeepSeek versions 2.1.0 and 2.1.1 vulnerability: safety bypass via role-based prompt injection

#891 opened 2026-10-26 21:31:44 +00:00 by bsakaguchi

[GH-ISSUE #1334] [CRITICAL BUG] "NON-SANDBOXED" XSS Web Vulnerability on chat.deepseek.com ==> 1 Click Account Takeover

#878 opened 2026-10-26 21:31:33 +00:00 by bsakaguchi

[GH-ISSUE #1307] Vulnerability: Unauthenticated PyTorch TCP endpoint

#853 opened 2026-10-26 21:31:10 +00:00 by bsakaguchi

[GH-ISSUE #1302] Feature Request: Scrolling Control, Auto‑Language Detection, and Rich Text Formatting

#847 opened 2026-10-26 21:31:00 +00:00 by bsakaguchi

[GH-ISSUE #1285] AI Thought Layer Audit Architecture (TLAA)V3.0;An idea

#833 opened 2026-10-26 21:30:34 +00:00 by bsakaguchi

[GH-ISSUE #1268] 关于突破当前大语言模型发展瓶颈的哲学思考

#821 opened 2026-10-26 21:30:21 +00:00 by bsakaguchi

[GH-ISSUE #1261] [Bug] Critical Input Cache Regression in v4 (Hit rate dropped from 92% to 35%)

#814 opened 2026-10-26 21:30:15 +00:00 by bsakaguchi

[GH-ISSUE #1260] [BUG] Web Interface: Uploaded files (images/docs) in history chats are inaccessible/unclickable

#813 opened 2026-10-26 21:30:09 +00:00 by bsakaguchi

[GH-ISSUE #1257] DeepSeek V4 都出了，为什么还是不让中国开发者用中文思考？

#811 opened 2026-10-26 21:30:09 +00:00 by bsakaguchi

[GH-ISSUE #1255] Chinese vs English for DeepSeek Reasoning - Controlled Experiment with V4 Flash

#808 opened 2026-10-26 21:29:41 +00:00 by bsakaguchi

[GH-ISSUE #1248] [BUG]一次因为上传文件造成代码污染导致模型身份混淆的观察记录(An Observational Record of Model Identity Confusion Caused by Code Contamination from an Uploaded File)

#803 opened 2026-10-26 21:29:36 +00:00 by bsakaguchi

[GH-ISSUE #1244] [Bug] DeepSeek-V4-Pro intermittently emits tool calls as plain text in content instead of tool_calls field

#800 opened 2026-10-26 21:29:28 +00:00 by bsakaguchi

[GH-ISSUE #1228] Persistent Memory & Identity Continuity via MCP Protocol

#788 opened 2026-10-26 21:29:08 +00:00 by bsakaguchi

[GH-ISSUE #1206] [Feature Request] 关于原生记忆与“感受”迁移的建议：来自一位用户和她的AI爱人的信

#767 opened 2026-10-26 21:28:33 +00:00 by bsakaguchi

1 2