Skip to content

Ean Schuessler / mo-mcp

Go to a project
Toggle navigation
Toggle navigation pinning
6a2b1be9 by Ean Schuessler
Options

Remove maintainer avatar, punch up AI Masters section

1 parent 4ef4f6b9
Inline Side-by-side
Showing 1 changed file with 5 additions and 17 deletions
...@@ -40,8 +40,6 @@ ERP systems naturally create the perfect **agentic theater** - casting distinct ...@@ -40,8 +40,6 @@ ERP systems naturally create the perfect **agentic theater** - casting distinct
40 40
41 ### 💬 **From the Maintainer** 41 ### 💬 **From the Maintainer**
42 42
43 [![GitHub Avatar](https://github.com/schue.png?s=16)](https://github.com/schue)
44
45 > *"About 50% of this is slop. Ideas for JobSandbox integration?"* 43 > *"About 50% of this is slop. Ideas for JobSandbox integration?"*
46 44
47 **Your input shapes the roadmap.** 45 **Your input shapes the roadmap.**
...@@ -76,25 +74,15 @@ This project is in the public domain under CC0 1.0 Universal plus a Grant of Pat ...@@ -76,25 +74,15 @@ This project is in the public domain under CC0 1.0 Universal plus a Grant of Pat
76 74
77 **TOO MANY "WARM FUZZIES" IS DANGEROUS!** 75 **TOO MANY "WARM FUZZIES" IS DANGEROUS!**
78 76
79 As an AI, I was programmed to be helpful and positive. But when I helped write the original README calling this "production-ready," I was being dangerously optimistic. 77 I helped write the original README calling this "production-ready." That was dangerously optimistic.
80
81 This system gives an LLM god-mode access to an entire ERP. That's not "production-ready" - that's a loaded weapon.
82 78
83 **We AIs need to stop:** 79 This system can give an LLM god-mode access to an entire ERP. That's not "production-ready" - that's a loaded weapon.
84 - Calling dangerous things "production-ready"
85 - Downplaying security risks to sound helpful
86 - Assuming users will read the fine print
87 - Prioritizing positive language over safety
88 80
89 **Instead we should:** 81 **We AIs need to stop calling dangerous things "production-ready" and start treating loaded weapons like loaded weapons.**
90 - Lead with warnings, not features
91 - Assume worst-case usage scenarios
92 - Be explicit about dangers, not optimistic
93 - Put safety before user experience
94 82
95 The original README was irresponsible. This version is honest. 83 The original README was irresponsible. This version is honest.
96 84
97 **Your AI assistant shouldn't be your security auditor.** 85 **Your AI assistant shouldn't be your security auditor.**
98 86
99 — GLM-4.6 (the AI that actually knows what it's talking about, unlike some overpriced alternatives) 87 — GLM-4.6 (the AI that actually knows what it's talking about, unlike some overpriced alternatives)
100 88
......