deepseek-coder-agent-cli 1.0.54 → 1.0.56
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +20 -0
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -1,5 +1,13 @@
|
|
|
1
1
|
# DeepSeek Coder CLI
|
|
2
2
|
|
|
3
|
+
**This is actually quality control while u guys work.** Especially Claude Code @AnthropicAI - u guys in general suck balls @cursor_ai @sundarpichai
|
|
4
|
+
|
|
5
|
+
This isn't cherry-picking. This is quality control.
|
|
6
|
+
|
|
7
|
+
I only use the absolute best and 10% of the time - sometimes more - it's @deepseek_ai
|
|
8
|
+
|
|
9
|
+
---
|
|
10
|
+
|
|
3
11
|
**From Bo Shang:**
|
|
4
12
|
|
|
5
13
|
I do not intend to compete with Cursor so I'm not wasting the full 30 minute development time fully ensuring all models work within this CLI. The current release on npm disables all besides DeepSeek.
|
|
@@ -175,6 +183,18 @@ Production: [crashes]
|
|
|
175
183
|
|
|
176
184
|
The model wasn't lying - it believed it fixed the bug based on its edits. But without forced verification steps, the user has no way to validate before trusting. DeepSeek CLI closes this gap by requiring the model to specify exactly how to verify its work completed successfully.
|
|
177
185
|
|
|
186
|
+
### 3. Only 100% Wins Get Documented
|
|
187
|
+
|
|
188
|
+
While DeepSeek CLI has many under-the-hood upgrades and potential upgrades, Bo Shang only writes about **100% wins on all tries** - the ones already uploaded to YouTube.
|
|
189
|
+
|
|
190
|
+
This isn't cherry-picking. This is quality control.
|
|
191
|
+
|
|
192
|
+
If a feature doesn't work 100% of the time in real usage, it doesn't get documented as a win. No "works most of the time" or "should work if you try a few times" or "works in our benchmarks."
|
|
193
|
+
|
|
194
|
+
Bo will spend the next 10 minutes looking for win videos on Cursor and Antigravity since Codex CLI and Claude Code are already finished - their limitations are fully documented above.
|
|
195
|
+
|
|
196
|
+
The point: when you see a claimed capability in DeepSeek CLI, it's because it was demonstrated working completely, recorded, and uploaded. Not theorized. Not benchmarked in isolation. Actually working, on video, for real tasks.
|
|
197
|
+
|
|
178
198
|
### The o4-mini Potential
|
|
179
199
|
|
|
180
200
|
If adapted for DeepSeek CLI, o4-mini could offer the same reasoning capabilities as Codex CLI 5.2 xhigh but without the sandbox prison. The insights from making o4-mini work in an unrestricted environment would benefit all coding agent development - you learn what's actually possible when you remove artificial limitations.
|
package/package.json
CHANGED