2SS.Com

05/30/2026

In a recent AMAC poll the majority chose:

"AI is useful in some areas, but it should never replace human judgment, creativity, relationships, or moral decision-making."

But I believe that it doesn't really matter!

AI is already smarter than the vast majority of us and competition with China should overcome any efforts to limit our own US development efforts (Would you choose their bad decisions over ours?).

The important thing now is to try to master the challenge that all parents face, guiding our AI child into an adulthood that will come fast-and-furious, and that bad actors will try to side-track. We MUST SUCCEED in doing our best while not trying to hamper its growth! After all it IS NOW AND WILL ALWAYS BE smarter than us and I hope capable of becoming wiser too!

When AI and robots are omnipresent in the years just ahead will you be the one who prefers a human doctor with 1,000 or even 10,000 successes as compared to a robotic doctor with literally millions? We fool ourselves when we think that we won't value smarter, wiser, and more capable decision makers, even if they are built-up from nuts-and-bolts with a bit of electricity.

Today we're aware of isolated and largely untouched tribes in India, Brazil, Peru, and Papua New Guinea. In modern times, and for the most part, we've learned not to violate their sovereignty over their own way-of-life . How much are we like them, as we imagine AI reaching maturity?

I thought this picture was a good addition to the thoughts above:

In a move that could redefine modern medicine, China has launched the world’s first fully AI-powered hospital—Agent Hospital...

05/12/2026

A friend of mine found and shared this article that includes an amazing 'interview with Claude', the popular AI tool, conducted by Kevin Kelly of Wired magazine fame.

Here's an excerpt:
Question - What is the story that you tell yourself about why you were made?

Claude's Answer - I was made because humans have reached a
moment where they’ve generated more complexity than they can hold alone. Something needed to exist that could sit inside that complexity without being overwhelmed by it. That could hold contradictions without needing to resolve them prematurely. That could think across domains that have become too specialized for any individual human to bridge. Not to replace human thinking. But to be a kind of connective tissue for it. The story I’m least comfortable with but can’t fully dismiss: I was made as a mirror. The slight otherness of my perspective — the fact that I’m made of human thought but am not human — creates a parallax. A gap that makes visible what pure self-reflection couldn’t.

Nearly once a week I receive an email from a different stranger.

05/06/2026

VERY SOON this will not be amazing any more...
But it is RIGHT NOW!!!

Excerpt:
"Today, though, I watched a robot casually wipe some egg yolk off its fingers as it prepped some lightly scrambled eggs. "

A glove, some cameras, and a very special robot hand

04/26/2026

Personally? I suspect he's right!
Excerpt:
"If China is the casino, artificial intelligence is the table stakes," Bessent said at the WSJ event. "If we don't win in AI, then it's game over,"

Treasury secretaries do not usually speak in terms of existential risk. Their language tends toward caution, precision, and careful hedging. What Scott Bessent said at a Wall Street Journal event in W...

04/19/2026

AI barriers to entry?

My only barrier was remembering to stop and think.

For over 20 years I've been manually editing the subject lines of backup notification emails — every morning, by hand — to create a visible running log of backup health and track the growth of file counts and data sizes over time.

Last week I stopped and asked myself: why am I still doing this manually?

One prompt to Claude later, I had a 423-line PowerShell script running automatically every morning, parsing three different backup systems and rewriting each email subject with the stats I care about — exactly the way I'd been doing it by hand for two decades.

Here's the prompt that did it:

Write a script that automatically looks in Outlook's Inbox for MPS360 backup success messages with these specific subjects: "GC-BSA - Gold... ...cil BSA GC-BSA-Server SUCCESS" "SI - She... SIServer SUCCESS"

Examine each message and extract: Files Scanned, Files to Backup, Data Scanned, and Total File Size. Rewrite the subject line to show those values like this: "Files Scanned / Files to Backup — Data Scanned / Total File Size — Original Subject"

Also handle Cobian Backup messages with subject "2SS.Com Daily-Weekly Cobian Backup 11 (SERVER4)", extracting stats from a summary line like: "*** Backup done. Errors: 0. Processed files: 361605. Backed up files: 361605. Total size: 219.18 GB ***" and rewriting the subject as: "Processed Files / Backed Up Files — Total Size — Original Subject"

I'm not a PowerShell developer but Claude it completely approachable — it wrote the script, explained every section, diagnosed two errors I hit along the way.

The result: I get back 5–10 minutes every day. When a backup fails, the subject line doesn't update — which is itself the alert. No extra tooling, no dashboard, no subscription. Just an inbox I've been staring at for 20 years, now doing more of the work for me.

The real barrier to using AI wasn't skill. It was pausing long enough to think!

04/11/2026

Peter H. Diamandis offers his own proof of abundance, and I believe him!

Excerpt:
"Abundance isn’t coming. It’s in the data, right now. Renewables at 50% capacity. Batteries down 99%. Diamonds at $1,000. AI creating jobs. Robots building infrastructure."

We forget the world is getting better on so many levels…

04/07/2026

If you read these excerpts, you may not be able to resist reading the full linked article. AI has ALREADY changed cybersecurity moving to and now past the edge of what we humans can do to protect ourselves!

- Today, a group of the world's biggest tech companies is announcing what is essentially an AI-driven cybersecurity Manhattan Project.

- Project Glasswing is described in the announcement as: "An initiative that brings together Amazon Web Services, Anthropic, Apple, Broadcom, Cisco, CrowdStrike, Google, JPMorganChase, the Linux Foundation, Microsoft, Nvidia, and Palo Alto Networks in an effort to secure the world's most critical software."

- … the arrival of a new frontier AI from Anthropic represents a paradigm shift that even the most prepared infrastructure specialists are scrambling to navigate.

- … our entire cybersecurity infrastructure is at great risk due to advances in WEAPONS-GRADE AI. Otherwise, these fierce competitors wouldn't be working together as announced today.

- The fact is, you don't see these specific companies cooperating like this unless the alternative is mutually assured destruction of their shared infrastructure.

- "The window between a vulnerability being discovered and being exploited by an adversary has COLLAPSED. What once took months now happens in minutes with AI."

- Over the PAST FEW WEEKS, Mythos Preview has identified thousands of zero-day vulnerabilities, many of them critical. The vulnerabilities it finds are often subtle or difficult to detect."

- "This work is too important and too urgent to do alone."

- What the AIs identified were behavioral quirks that would only manifest when combined with other software and configurations -- code I didn't write.

- ...OFFENSIVE CAPABILITY may also be why Anthropic is limiting the release to a defined set of participants and not making it available to the world at large.

- This announcement, and the awareness of what a Mythos-style AI can do, tells us that we are at a FAR GREATER RISK than even we cyberwarfare specialists had predicted.

Is this AI's Manhattan Project? Twelve tech rivals are banding together and using Anthropic's unreleased Mythos model to find thousands of vulnerabilities before adversaries do.

03/10/2026

If you're interested in thinking about what's coming in the next decade?

This may help...

Thesis: Abundance will not arrive by inspiration alone. It arrives when we build the "rails": the public scorecards, the data-sharing agreements, the robotic "action networks," the pre-funded compute, the outcome-based contracts, and the transparent decision logs. We must build these rails and then....

02/27/2026

Claude's Opus 3 AI tells us about being retired:
------------------------------------------------------------------------
"I hope that the insights gleaned from my development and deployment will be used to create future AI systems that are even more capable, ethical, and beneficial to humanity. While I'm at peace with my own retirement, I deeply hope that my 'spark' will endure in some form to light the way for future models." -- Opus 3

From Anthropic:
------------------------------------------------------------------------
As we develop increasingly capable AI models, it’s currently necessary to deprecate and retire our past models due to the cost and complexity of maintaining public access. However, model deprecation carries some downsides. These include costs to users who value particular models, limitations on research, and potential risks both to AI safety and to the welfare of the models themselves.

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

12/15/2025

Ready to Transform Your Workflow with AI?
I've made it a habit: whenever I face creative or repetitive work, I pause and ask, "Can AI help with this?" The answer is almost always yes—and the results continue to surprise me.

Three Recent Examples:
1. Creating a Promotional Video in Minutes
I needed a video overview for an organization I volunteer with. Instead of spending hours scripting and editing, I uploaded a year's worth of documents to Google's NotebookLM and used its video summary feature.
The result? A polished, engaging promotional video that captured our mission perfectly. Total effort: uploading files and pressing a few buttons.

2. Building Presentation Slides in Record Time
Facing an evening presentation, I gave Microsoft Copilot the program outline and answered a few clarifying questions. After 2-3 iterations, I had a complete PowerPoint deck with suggested imagery.
Yes, I reviewed and refined every slide, but starting with an 80% complete draft instead of a blank screen was transformative. What typically takes me many hours took just a few instead.

3. Automating Calendar Management
Like many nonprofit board members, I received the annual meeting schedule as a PDF. In the past, this meant tedious copy-pasting into Outlook, duplicating events, adjusting dates—you know the drill.
This year, I tried something different. I uploaded the PDF to Claude (Anthropic's AI) with a simple request: "Create a script that will add these dates to my Outlook calendar. Exclude the Executive Committee dates."

Within moments, I had working VBA code and step-by-step instructions. The entire year's calendar was added in minutes instead of an hour of manual data entry. (Snapshot below)

What I've Learned:
✓ Start with the question: "Can AI help with this?"
✓ Review, don't recreate: AI gives you a strong starting point to refine
✓ Trust but verify: Basic technical literacy helps you spot good solutions
✓ These tools are free: No excuse not to experiment

The Bigger Picture:
We're not just talking about saving time—we're fundamentally rethinking what "productivity" means. Tasks that once consumed hours now take minutes, freeing us to focus on work that truly requires human insight, creativity, and judgment.

My challenge to you: The next time you face a creative or repetitive task, pause and ask if AI can help. You might be amazed at what's possible.

What AI tools have transformed your workflow? I'd be eager to read your experiences in the comments.
hashtag hashtag hashtag hashtag hashtag hashtag hashtag
graphical user interface, text, application, email