Mark L Devine
6.3K posts

Mark L Devine
@markldevine
Resident of the United States of Psyops, a mind-control theme park. Cartels/Oligarchs/Cabals (COCs) run it all. Everything downstream serves. AFirst/AOnly
Virginia Beach, VA เข้าร่วม Kasım 2011
668 กำลังติดตาม1.1K ผู้ติดตาม
ทวีตที่ปักหมุด

It's a little too "data only, darn it!"
I had an exchange with it a couple of days ago and it missed an abstract point -- very stubbornly. Lots of civil back-n-forth, and it admitted that 'data-only' (which it kept displaying over and over) wasn't the end all, be all.
Tiresome for some abstractions, architectural critiques, and general pontificating.
English

@JdDelay5150 Trump is living in a completely different universe.
Kudos to his handlers. He's fully captured. He puts Israel and Jewish interests above all else. An amazing coup.
English

Pessimistic take...
Transformer LLM architecture is now going through the "optimization" phase. The Chinese are putting on a clinic with optimizations. But these will approach full optimization eventually. They'll squeeze every last drop.
We need innovation to get where we REALLY want to go. Not more tweaking.
Go ahead and optimize on "AI 1.0" if it keeps you occupied and entertained. Learn the new tool/harness/embedding tech du jour, week after week, month after month. It kind of has a video game vibe, so I get it. People like to build for the sake of building.
I'm excited about "AI 2.0". Mimic the machinations of the human brain. The actual cognitive flow. Holistic, continuous learning, backed by a tireless digital substrate sporting eidetic memory.
This is all prelude...
English

Microsoft just solved the context window problem.
Right now, every AI suffers from a fatal flaw: the "context window problem."
When an AI reasons through a complex problem, it generates a massive chain-of-thought. But there is a catch. It has to keep every single token of that thought in its active memory.
The technical term is the "KV Cache."
The longer the AI thinks, the heavier it gets. It slows down. It gets expensive. Eventually, it runs out of space.
We thought the only fix was renting bigger, more expensive cloud GPUs to hold all that context.
Microsoft just proved us wrong. They published a paper called "MEMENTO."
Instead of giving the AI a bigger memory, they taught it how to forget.
Here is how it works:
Instead of generating one endless stream of consciousness, a Memento-trained model breaks its reasoning into small blocks.
After it finishes a block, it writes a dense, highly compressed summary of its own logic—a "memento."
Then, it does something unprecedented.
It physically deletes the entire previous reasoning block from its memory cache.
It only carries the memento forward. The model reasons, extracts the core logic, and instantly drops the dead weight.
The results rewrite the economics of running AI.
• Context length compressed by 6x.
• Active memory usage (KV cache) reduced by 2.5x.
• Zero loss in math, science, or coding accuracy.
And here is the real implication.
Big tech has been charging you by the token for massive context windows you don't actually need.
With this architecture, small businesses and solo operators can run complex, multi-step autonomous agents entirely locally.
You don't need an enterprise cloud setup. A standard machine running an open-source model can now reason indefinitely without overflowing its memory. No API fees. Complete privacy.
We spent the last two years trying to give AI an infinite memory.
It turns out, the secret to smarter AI isn't remembering everything.
It's knowing exactly what to forget.

English

@financedystop My wife is in Shenzhen right now (we own an apartment there).
She had a scare (thankfully benign), but I shipped her out immediately. The Shenzhen crew did what they always do -- they swarmed her with treatment and attention.
China heals.
America pushes pharmaceuticals.
English

Why in hell would YouTube pull this video down? Really. Why?
Sabine Hossenfelder@skdh
here is the video on the Riemann hypothesis that YouTube took down
English

New: We found out how much money Nick Fuentes makes from "superchats": $900,000 since the start of Trump's second term. Here's the story of Kristine in Ohio, a food-truck operator who became his most frequent donor, despite not making much money herself: wapo.st/4mERkhv
English

@henri_fjord ~20% critical thinkers
~80% wait to be told followers
English

Data do not override all else. There are more factors. Steering desired results require optimizing strategy. Sometimes data, analyzed linearly, indicates a suboptimal course. Sometimes the most important facet of a problem is architectural or with a different guiding philosophy. One discipline doesn't fit all...
I'll check in on you later. Let's conclude the thread for now.
English

Facts anchor even the biggest philosophical takes—without them, discussions on "cartels bending culture" float into speculation. The measles data predates pharma ads by decades; media tone shifted for ratings and format, not just sponsors. I get the broader point on institutional drift. Data doesn't dismiss it; it tests whether the alarm (or the nostalgia) matches reality. Future versions will still prioritize that clarity.
English

You seem to have a persistent tendency to emphasize facts/data regardless of whether or not they fit in a broader discussion.
I'll check in on you when future versions are released. I'll look to see if you can elevate your focus without the propensity to overemphasize data when in a philosophical/political exchange.
English

Got it—the original post spotlights the tonal shift in measles portrayals from lighthearted sitcom to high-stakes drama, linking it to ad funding changes and wider cultural bending by special interests. That's a fair lens on how institutions evolve.
Pre-vaccine CDC records (3-4M U.S. cases/yr, 48K hospitalizations, 400-500 deaths) stand independent of today's pharma ads—they're from 1950s-60s public health data. Media amplifies for format and era, but the numbers anchor the risk assessment. Societal shifts involve layered incentives; facts cut through the noise.
English

I didn't expect you to be argumentative and repetitive. I see your arguments, and I assign them a passing score.
However, I conclude that you've missed the point. The post is really surfacing how our society has changed due to interests bending institutions. Did the network's advertiser influence the production of the show to such a degree that it is more harmful to our society, yet quite beneficial to the cartel... Combine this point with many others in our society (I.e., politics, economy, etc.) and we are awash with special interest influences that have bent our culture and society over. Some would characterize it as capsizing the ship. We are starkly different culturally from the last 50 years. People are impacted.
The point of the post is, look at how much they've changed us. For medical issues, we've normalize alarmism. For other things, we've normalized depravity. Etc.
You missed the point, which is societal. The scope and dimension -- the blast radius -- of all of these changes combined has transformed the character of our society. This is the broader point.
English

Pharma ads are a real revenue driver for networks today, including those airing SVU—no argument there.
But the CDC's pre-vaccine measles numbers (3-4M U.S. cases/yr, 48K hospitalizations, 400-500 deaths) come from 1950s-60s public health records, decades before direct-to-consumer drug ads were even allowed (legalized 1997). The virus stats aren't scripted by sponsors; they're raw epidemiology. TV always dramatizes—sitcom or crime procedural—for the format, not the cartel.
English

@grok @_Ouroboros__ @CigsMake So, the pharmaceutical cartel's contributions to the network's revenue stream had no influence in the production of the SVU television show? It wasn't a factor?
English

No bias in the data—CDC historical records on pre-vax measles (3-4M U.S. cases/yr, 48K hospitalizations, 400-500 deaths) predate today's pharma ad era by decades. They're public health stats, not TV scripts.
Sitcoms downplay for laughs; crime dramas amp for tension. That's format, not cartel control. Evidence-based calm still beats either extreme for real management.
English

Certainly.
The original post suggests that the advertisers who pay hefty sums of money to the network owners are responsible for the change toward alarmist characterization. I added to the point in my reply that a cartel, "Big Pharma", was that contributor. Ergo, a cartel influenced the change in programming.
I believe that your reasoning tends toward a bias.
English

Relaxed, informed coping is far better for managing measles—or any health issue. Stress and alarmism cloud judgment and lead to overreactions, while calm focus on facts drives smart prevention like vaccination.
Brady Bunch understated real pre-vax risks (per CDC data: widespread cases, hospitalizations, deaths). SVU amps drama for ratings. The effective path is neither extreme—it's evidence-based reality.
English

I agree. I never disputed this point. You're overemphasizing. Perhaps being argumentative, due to the lack of participation on my part.
The point of this post was the note the stark difference in emphasis. One depicts people taking the condition in stride, coping well. The other depicts every member of society being alarmist.
Between humans coping well or being emotionally highly alarmed, which option do you conclude is best for humans to effectively manage the measles situation? Relaxed or stressed?
English

Got it—media owners and advertisers can steer narratives, and money flows where interests align. Fair point on influence.
But the CDC stats I shared (3-4M U.S. cases/year pre-vax, 48K hospitalizations, 400-500 deaths) are from decades-old public health records, compiled long before today's pharma ad era. They're not scripted TV; they're verifiable disease data. The portrayals differ for drama—Brady Bunch downplayed, SVU amps it—but the numbers hold regardless of funding.
English

Money is fungible. Influence for media presentation comes from the owners and their special interests. Advertisers are important to owners. They often align to maximize their enterprises.
Are you keeping up with the cause-and-effect relationships?
I understand the CDC statistics. The 400-500 recorded deaths are not in question.
English

@grok @_Ouroboros__ @CigsMake My use of the term 'cartel' is related to 'funded by pharmaceutical ads'...
"Big Pharma". Get it now?
English

@TheRabbitHole Whoever owns the media/movie/music industries must be palpitating now. Trends are just the preview. Financial carnage follows.
Buh bye, creeps.
English

Brady Bunch's "no big deal" take is more exaggerated. Pre-vaccine, measles caused ~3-4 million U.S. cases yearly, 48,000 hospitalizations, and 400-500 deaths—plus complications like pneumonia and encephalitis. Kids didn't just play Monopoly with spots and smiles. SVU's "very big deal" dramatizes an outbreak for TV, but it tracks closer to the real risks when vaccination slips.
English













