Sando George

948 posts

Sando George banner
Sando George

Sando George

@sandogee

Futurist | Software Engineer | Strategic Advisor | Military Officer Opinions are my own.

The City of Gold شامل ہوئے Aralık 2010
651 فالونگ102 فالوورز
پن کیا گیا ٹویٹ
Sando George
Sando George@sandogee·
Pin: My weekly series (pragmatic, reflective): Mon - Decision Craft Tue - Systems Thinking Wed - Signals & Sensemaking Thu - Resilience & Readiness Fri - Foresight Sat - Strategy Studio Sun - AI & Thinking Daily: Current Affairs Everyday briefs (cross-cutting).
English
1
0
3
103
Sando George ری ٹویٹ کیا
Marcin Paprzycki
Marcin Paprzycki@marcinpaprzycki·
ENERGIES (MDPI) told me that I should promote my work ... They published it... so, here is the promotion ;-) Title: Dynamic Knowledge Management in an Agent-Based Extended Green Cloud Simulator Link: mdpi.com/1996-1073/17/4…
English
1
2
2
55
Sando George
Sando George@sandogee·
The current wave of vibe-coded AI systems resembles the spreadsheet era in how it decentralizes capability and embeds critical business logic outside formal engineering controls, but with a more opaque and potentially more hazardous failure surface.
English
0
0
0
10
Sando George
Sando George@sandogee·
Grok isn’t being judged on “AI potential.” It’s being judged on the distribution loop: personal data → generation → virality → harm. EU/UK regulators are testing whether “safety by design” is real or just a blog post. Where should liability sit?
English
1
0
0
20
Sando George
Sando George@sandogee·
Is 100% test coverage still unrealistic/suboptimal when it's agents designing and writing tests?
English
1
0
0
29
Sando George
Sando George@sandogee·
@marcinpaprzycki Full agreement that formal verification is the only TRUE 100% test. I'm mainly referring to common unit/integration testing here though. I decided to try and was able to get one of my code bases to 100% in about 12hrs using GPT-Codex-5.3. I had done about 53% manually.
English
1
0
0
37
Marcin Paprzycki
Marcin Paprzycki@marcinpaprzycki·
@sandogee Yes, it is as there is no way to imagine everything and/ or it will take forever. The only 100% test is formal verification.
English
1
0
0
24
Sando George
Sando George@sandogee·
It just hit me that we're probably not authoring GitHub project readmes for humans anymore.
English
0
0
0
20
Sando George
Sando George@sandogee·
GPT-5.3-Codex. The vibe is strong with this one. This is the way.
English
0
0
0
63
Sando George
Sando George@sandogee·
@Jayyanginspires Writing forces a level of accountability that is often ignored when speaking.
English
0
0
0
4
Sando George
Sando George@sandogee·
Remember when boilerplate generation tools made you feel good as a coder?
English
0
0
0
30
Sando George
Sando George@sandogee·
So will the mythical 10x engineer now be replaced by a solid 1x engineer doing agentic coding?
English
0
0
0
31
Sando George
Sando George@sandogee·
For years I've thought of the idea of cloning myself to get more work done. Now we have fairly capable agents that are easy to spin up and direct. I'm happy.
English
0
0
0
27
Sando George
Sando George@sandogee·
Reading: arxiv.org/pdf/2601.09760 — shows how tool vs memory conflicts can quietly break reliability; provenance makes the mismatch visible.
English
0
0
0
21
Sando George
Sando George@sandogee·
Reading: arxiv.org/pdf/2601.20727 — argues for “LLM audit trails” (tamper-evident provenance) as a practical accountability mechanism.
English
1
0
0
35
Sando George
Sando George@sandogee·
AI will draft you a plan that sounds like it survived a staff brief. But if you can’t trace where each claim came from, you’re outsourcing judgment—not typing. Habit: demand provenance (“source / assumption / confidence”) before you act.
English
1
0
0
28

دریافت کریں

@marcinpaprzycki @Jayyanginspires @elonmusk @BarackObama @taylorswift13 @cristiano @BillGates @NASA