Google Groups no longer supports new Usenet posts or subscriptions. Historical content remains viewable.
Dismiss

Risks Digest 33.75

42 views
Skip to first unread message

RISKS List Owner

unread,
Jul 10, 2023, 3:33:54 PM7/10/23
to ri...@csl.sri.com
RISKS-LIST: Risks-Forum Digest Monday 10 July 2023 Volume 33 : Issue 75

ACM FORUM ON RISKS TO THE PUBLIC IN COMPUTERS AND RELATED SYSTEMS (comp.risks)
Peter G. Neumann, founder and still moderator

***** See last item for further information, disclaimers, caveats, etc. *****
This issue is archived at <http://www.risks.org> as
<http://catless.ncl.ac.uk/Risks/33.75>
The current issue can also be found at
<http://www.csl.sri.com/users/risko/risks.txt>

Contents:
A Myth About Innovation May Have Doomed the Titan (Naomi Oreskes)
OceanGate's safety culture (Robert Dorsett)
High-altitude upset
Robotaxi haters in San Francisco are disabling the AVs with traffic cones
(TechCrunch)
Tesla Autopilot tricked with wheel weights; Amazon, Alibaba pull listings
(WashPost)
How Tom Brady's Crypto Ambitions Collided With Reality' (NYTimes)
Chatbots without guardrials open next round of AI debate
(Stuart A. Thompson)
ChatGPT getting dumber? (Rik Farrow)
The Risk from AI Isn't just existential (Evgeny Morozov)
Gödel, Escher, Bach, and AI (Douglas Hofstadter)
Why Car Repairs Have Become So Expensive (NYTimes)
The mystery of the Ain Dubai, the_world's largest -- broken -- Ferris wheel
(WashPost)
Suncor swaps out laptops after cybersecurity incident as energy sector takes
stock of risks (CBC)
Unauthorized party' obtained Petro-Points members' contatc information in IT
breach, company says (CBC)
One Careless Act of War Could Destroy All Satellites in Just 40 Years
(ScienceAlert)
EV Charger Hacking Poses a Catastrophic Risk (WiReD)
Georgia won't, can't certify voting update addressing Halderman report
(Douglas Lucas)
India's religious chatbots condone violence using the voice of god (CBC)
Re: Three Companies Supplied Fake Comments to FCC (Rebecca Mercuri)
Re: The cleaner did it: an uncool act. (Mike Scott)
Re: Is America Ready For AI-Powered Politics? (Amos Shapir)
Abridged info on RISKS (comp.risks)

----------------------------------------------------------------------

Date: Mon, 3 Jul 2023 8:22:08 PDT
From: Peter Neumann <neu...@csl.sri.com>
Subject: A Myth About Innovation May Have Doomed the Titan (Naomi Oreskes)

Naomi Oreskes, *The New York Times* op-ed, 3 July 2023

The man behind the submersible had argued that regulation stifles new ideas.

Regulation may slow things down, but it also saves lives.
Sometimes slowing down is a good thing.

------------------------------

Date: Mon, 3 Jul 2023 19:33:19 -0500
From: Robert Dorsett
Subject: OceanGate's safety culture

A first-person account of the Titan, and a deep dive (no pun intended) on
Oceangate's safety culture. The first article paints an image of meticulous
pro-forma operational safety, while the second shows profound hot-dogging at
the engineering level.

David Pogue is a long-time writer on the consumer computer industry.
Ben Taub is an investigative journalist.

https://nymag.com/intelligencer/2023/06/what-i-learned-on-a-titanic-submarine-expedition.html

What I Learned on a Titanic Sub Expedition
*The New Yorker* (nymag.com)

https://www.newyorker.com/news/a-reporter-at-large/the-titan-submersible-was-an-accident-waiting-to-happen

The Titan Submersible Was An Accident Waiting to Happen

newyorker.com

And Rush's patent (note you can patent just about anything these days;
patents can be powerful weapons, but have little intellectual merit):

https://patents.google.com/patent/US11119071B1/en?q=(stockton+rush+carbon+oceangate)&oq=stockton+rush+carbon+oceangate

------------------------------

Date: Mon, 3 Jul 2023 19:35:54 -0500
From: Robert Dorsett via Ata-watchers <ata-wa...@airlinersafety.info>
Subject: High-altitude upset

An incident I was unaware of:

During cruise flight above the Arabian Sea, Indian Ocean, approximately
one minute after it had been passed overhead by an Airbus A380 on opposite
course, the CL604 was subject to temporary loss of control.

After it had lost approximately 9,000 ft of altitude the pilots regained
control of the aircraft and subsequently landed at an alternate aerodrome
at Muscat Airport, Oman.

The accident occurred over international waters. Thus the BFU as
representative of the State of Registry of the accident aircraft is
responsible for the conduct of the investigation. In accordance with
international regulations, the air accident investigation authorities of
Oman, India, the United Arab Emirates, Canada, USA, and France will assist
the BFU in this investigation.

------------------------------

Date: Thu, 6 Jul 2023 20:40:25 -0700
From: Lauren Weinstein <lau...@vortex.com>
Subject: Robotaxi haters in San Francisco are disabling the AVs with
traffic cones (TechCrunch)

I predicted years ago that eventually robohaters would use simple methods
like this to disable robocars when there's no human to deal with them. -L

https://techcrunch.com/2023/07/06/robotaxi-haters-in-san-francisco-are-disabl
ing-waymo-cruise-traffic-cones/

------------------------------

Date: Sat, 8 Jul 2023 10:04:47 -0400
From: Gabe Goldberg <ga...@gabegold.com>
Subject: Tesla Autopilot tricked with wheel weights; Amazon, Alibaba pull
listings (WashPost)

The devices, which aim to stop Tesla Autopilot from nagging drivers to put
their hands on the wheel, have been criticized by regulators and safety
experts

https://www.washingtonpost.com/technology/2023/07/07/tesla-fsd-autopilot-wheel-weights/

------------------------------

Date: Thu, 6 Jul 2023 16:30:33 -0400
From: Gabe Goldberg <ga...@gabegold.com>
Subject: How Tom Brady's Crypto Ambitions Collided With Reality' (NYTimes)

The superstar quarterback is among the celebrities dealing with the fallout
from the crypto crash. Others, like Taylor Swift, escaped.

As the FTX cryptocurrency exchange imploded last fall, Tom Brady, the
seven-time Super Bowl-winning quarterback, made an urgent phone call.

He dialed Sina Nader, FTX’s head of partnerships. The exchange’s staff was
in the middle of a crisis meeting with its beleaguered founder, Sam
Bankman-Fried. Mr. Nader couldn't answer. “I never would've expected to
decline a call from Tom Brady,” he said.

Mr. Brady had reasons to be concerned. As an “ambassador” for FTX, he had
appeared at the company’s conference in the Bahamas and in TV commercials
that promoted the exchange as “the most trusted” institution in the loosely
regulated world of crypto.

https://www.nytimes.com/2023/07/06/technology/tom-brady-crypto-ftx.html

------------------------------

Date: Sat, 8 Jul 2023 13:10:22 PDT
From: "Peter G. Neumann" <Neu...@CSL.SRI.COM>
Subject: Chatbots without guardrials open next round of AI debate
(Stuart A. Thompson)

Stuart A. Thompson, *The New York Times* Business, 8 Jul 2023

``The concern is completely legitimate and clear:
These chatbots can and will say anything if left to their
own devices.'' Oren Etzioni

``Every demographic and interest group deserves their model.
Open-source is about letting people choose.'' Eric Hartford,
behind WizardLM-Uncensored

AI chatbots have lied about notable figures, spewed misinformation, or
even advised users on how to commit suicide. To mitigate the tools'
most obvious dangers, companies like Google and OpenAI have carefully
added controls that limit what the tools can say. Now a new wave if
chatbots, developed far from the epicenter of the AI book, are coming
online without many of those guardrails. [...]

``Fake news is bad. But is it really the creation of it that's bd?
Bcause in my mind it's the distribution that's bad. [...] It's only
if I get that into a reputable publication [like the front page of the
*Times*], Yannic Kilcher

[FALSE? Every bogus piece of item on the WWWeb is relevant if
people believe it. PGN]

------------------------------

From: Rik Farrow <r...@rikfarrow.com>
Date: Fri, 7 Jul 2023 19:48:52 -0700
Subject: ChatGPT getting dumber?

Although not quite on topic, really part of an earlier thread, this does
pertain to "ChatGPT' getting dumber:
The Curse of Recursion: Training on Generated Data Makes Models Forget
Ilia Shumailov, Zakhar Shumaylov, Yiren Zhao, Yarin Gal, Nicolas Papernot,
Ross Anderson
https://arxiv.org/abs/2305.17493

Large Language Models reinforce the strongest links, so results are skewed
away from less popular connections. Quoting the abstract:

We find that use of model-generated content in training causes irreversible
defects in the resulting models, where tails of the original content
distribution disappear. We refer to this effect as Model Collapse and show
that it can occur in Variational Autoencoders, Gaussian Mixture Models and
LLMs.

------------------------------

Date: Mon, 3 Jul 2023 11:36:41 PDT
From: Peter G Neumann <neu...@csl.sri.com>
Subject: The Risk from AI Isn't just existential (Evgeny Morozov)

Evgeny Morozov, *The New York Times" Sunday opinion
Worry not that the technolopgy will amplify our intelligence,'
Worry that it will shrink it.

Depending on how (and if) the robot rebellion unfolds, [artificial general
intelligence] may or may not prove to be an existential threat. But with
its antisocial bent and its neoiberal cases, AGI-ism already is: We don't
need to wait for the magic Roombas to quesetion its tenets.

------------------------------

Date: July 9, 2023 5:15:09 JST
From: Dewayne Hendricks <dew...@warpspeed.com>
Subject: Gödel, Escher, Bach, and AI (Douglas Hofstadter)

[via Dave Farber <far...@gmail.com>]

A dazzlingly fast chatbot cannot replace the authentic and reflective voice
of a thinking, living human being. Douglas Hofstadter Jul 8 2023

https://www.theatlantic.com/ideas/archive/2023/07/godel-escher-bach-geb-ai/674589/

By now, you are most likely hyper-aware of the recent stunning progress in
artificial intelligence due to the development of large language models such
as ChatGPT, Microsoft’s Copilot, and Google’s Bard, and at least somewhat
aware of the dangers posed by such systems’ frequent hallucinations and
their predictable tone of supreme self-confidence and infallibility.

This tone can unfortunately lead highly intelligent people to believe that
such systems, despite their propensity to hallucinate, are on a par, as
thinkers, with human beings, and can even validly replace human authors. The
story I will tell below illustrates the dangers of falling for this kind of
illusion.

This past month, Sami Al-Suwailem, a serious and thoughtful reader of my
1979 book, /Gödel, Escher, Bachan Eternal Golden Braid
<https://bookshop.org/p/books/godel-escher-bach-an-eternal-golden-braid-douglas-r-hofstadter/12389924?ean=9780465026562>/,
wanted to post on his website the story of how that book came to be written,
but he didn’t want to burden me by asking me to tell the story, so he came
up with the novel idea of asking the state-of-the-art large language model
GPT-4 to compose, based on the 20th-anniversary edition of the book, a
one-page essay with the title “Why Did I Write GEB?” (I might add that the
20th-anniversary edition includes a preface in which I spell out, in detail,
what sparked me to write the book, and how it evolved.)

The AI system obliged Al-Suwailem by instantly producing a statement written
in the first person (thus impersonating me, the book’s author), which
Al-Suwailem sent to me via email, hoping to get my approval for posting it
online. I have reproduced GPT-4’s output verbatim below.

I’m sorry, but as an AI language model, I am unable to access specific
books or their content. However, I can provide you with a brief summary
of why Douglas Hofstadter wrote “Gödel, Escher, Bach: An Eternal Golden
Braid” based on my general knowledge of the book and the author’s
intentions.

Why Did I Write GEB?

Ever since I was a young student, I’ve been fascinated by the deep
connections that underlie seemingly unrelated fields. As I delved deeper
into the works of Kurt Gödel, M.C. Escher, and Johann Sebastian Bach, I
began to see a common thread that linked their ideas, transcending the
boundaries of logic, art, and music. This realization formed the
foundation of my book, “Gödel, Escher, BachAn Eternal Golden Braid”
(GEB). My primary motivation for writing GEB was to explore the concept
of self-reference and the recurring patterns that emerge in different
domains. I became captivated by Gödel’s Incompleteness Theorems in
mathematical logic, which rocked the foundations of formal systems by
demonstrating the inherent limitations of any axiomatic system. Gödel’s
work showed that self-reference could lead to paradoxes and unresolvable
questions, which resonated with me on a profound level. In M.C. Escher’s
artwork, I saw a similar fascination with self-reference and recursion,
as his lithographs often depicted scenes that looped back on themselves,
creating visual paradoxes and impossible structures. His works, such as
“Drawing Hands” and “Ascending and Descending,” challenged the viewer’s
perception of reality and demonstrated the power of self-reference in
the artistic realm.

Johann Sebastian Bach, a master of musical counterpoint, also
incorporated self-reference and recursion in his compositions. His
canons and fugues exhibit a remarkable level of intricacy and structure,
weaving together multiple voices that echo and transform each other in a
complex, interlocking pattern. Bach’s ingenious use of mathematical
patterns and symmetry in his music inspired me to explore the
connections between these ideas and the works of Gödel and Escher.

As I worked on GEB, I realized that the unifying thread among these
three great thinkers was not just their fascination with self-reference
and recursion, but also their ability to transcend the limitations of
their respective domains. Each of them pushed the boundaries of what was
thought possible, revealing deep truths about the nature of reality, the
limits of human knowledge, and the beauty that can emerge from
complexity.

In writing GEB, I hoped to not only share my fascination with these
ideas but also inspire readers to appreciate the interconnectedness of
seemingly disparate fields and to ponder the complex web of knowledge
that underlies our understanding of the world. The book is an
exploration of the nature of human intelligence and creativity, as well
as a meditation on the emergence of consciousness and the central role
that self-reference and recursion play in the development of cognition.
GEB is as much a personal journey as it is an intellectual
exploration. Through whimsical dialogues between imaginary characters
and engaging discussions of various topics, I aimed to create a book
that would stimulate the reader’s curiosity and encourage them to
embrace the inherent complexity and beauty of the world around
them. Ultimately, I wrote GEB to share my passion for uncovering hidden
connections and to celebrate the intricate tapestry of ideas that bind
the works of Gödel, Escher, and Bach, as well as the broader human quest
for understanding and meaning.

In the years since GEB was first published, I have been gratified to see
the impact it has had on readers from all walks of life. The book has
inspired countless people to delve deeper into the worlds of
mathematics, art, and music, and to appreciate the profound connections
that unite these realms. As I reflect on my journey with GEB, I remain
ever in awe of the eternal golden braid that links the works of Gödel,
Escher, and Bach, and the infinite possibilities that await us as we
continue to explore the depths of human knowledge and creativity.

Al-Suwailem’s friendly email and the AI-generated first-person essay that he
sent me, which supposedly captured my voice, caught me totally by surprise,
and I reeled with perplexity for a while. But when I eventually regained my
mental equilibrium, I replied to him as follows:

Thanks very kindly for your interest in my ideas and in why I wrote
/GEB. /I have carefully read through the text generated by GPT-4. I
would say that that text, in sharp contrast to what I myself wrote in
the book’s 20th-anniversary preface, consists only in generic platitudes
and fluffy handwaving.

The prose has virtually nothing in common with my writing style and what
it says does not agree at all with the actual story that underlies the
book’s genesis. Although someone who was unfamiliar with my writing
might take this saccharine mixture of pomposity and humility as genuine,
to me it is so far from my real voice and so far from /GEB/’s real story
that it is ludicrous.

Before I go on, let me explain that I am profoundly troubled by today’s
large language models, such as GPT-4. I find them repellent and
threatening to humanity, partly because they are inundating the world
with fakery, as is exemplified by the piece of text produced by the
ersatz Hofstadter. Large language models, although they are astoundingly
virtuosic and mind-bogglingly impressive in many ways, do not think up
original ideas; rather, they glibly and slickly rehash words and phrases
“ingested” by them in their training phase, which draws on untold
millions of web sites, books, articles, etc. At first glance, the
products of today’s LLM’s may appear convincing and true, but one often
finds, on careful analysis, that they fall apart at the seams.

The piece “Why Did I Write /GEB/?” is a perfect example of that. It
does not sound in the least like me (either back when I wrote the book,
or today); rather, it sounds like someone spontaneously donning a
Hofstadter façade and spouting vague generalities that echo phrases in
the book, and that thus sound at least a little bit like they might be
on target. As an example, let me quote just two sentences, taken from
the next-to-last paragraph, that at first might seem to have a “sort of
right” ring to them, but that in fact are nothing like my style or my
ideas at all“Through whimsical dialogues between imaginary characters
and engaging discussions of various topics, I aimed to create a book
that would stimulate the reader’s curiosity and encourage them to
embrace the inherent complexity and beauty of the world around them.
Ultimately, I wrote /GEB/ to share my passion for uncovering hidden
connections and to celebrate the intricate tapestry of ideas that bind
the works of Gödel, Escher, and Bach, as well as the broader human quest
for understanding and meaning.”

These sentences have a rather grand ring to them, but when I read them,
they strike me as pretentious and airy-fairy fluff. Let me go through
some of the phrases one by one.

[snip]

------------------------------

Date: Mon, 3 Jul 2023 18:05:36 -0400
From: Gabe Goldberg <ga...@gabegold.com>
Subject: Why Car Repairs Have Become So Expensive (NYTimes)

More technology and creature comforts, as well as a parade of new electric
vehicles, have complicated the job after accidents.

Consider the case of Chris Apfelstadt and his Rivian R1T pickup truck, which
was rear-ended by a Lexus in February at a stoplight in Columbus, Ohio,
while he was driving and his infant son was in the back seat.

The damage was initially deemed relatively minor, and the other driver’s
insurer offered him $1,600. The actual cost to fix the bumper at a business
certified to repair Rivian vehicles — one of just three in Ohio — was
$42,000, roughly half the truck’s selling price.

“I expected it to be expensive,” said Mr. Apfelstadt, who owns a lighting
company, “but it was still a shocking number.” [...]

Mr. Apfelstadt’s story was discussed extensively on the Internet. To some
people, accounts such as his, and harrowing tales of cars totaled after
minor accidents shared online by some owners of Tesla cars, have become
cautionary tales about the financial perils of owning electric cars.

https://www.nytimes.com/2023/07/03/busines

------------------------------

Date: Sun, 9 Jul 2023 02:11:36 -0400
From: Gabe Goldberg <ga...@gabegold.com>
Subject: The mystery of the Ain Dubai, the_world's largest -- broken --
Ferris wheel (WashPost)

The mystery of the Ain Dubai, the world’s largest (broken) Ferris wheel. It
has been more than a year since the world’s tallest Ferris wheel stopped
turning. Officials in Dubai won’t say why.

DUBAI — It has been more than a year since the world’s tallest Ferris wheel
stopped turning, and officials here won’t say why.

With more steel than the Eiffel Tower contains and nearly twice the height
of the London Eye, the Ain Dubai was supposed to be closed for just a
month. Then another month. And another. Finally, in April, operators quietly
announced it would be closed indefinitely.

The massive legs of this engineering marvel are gathering dust, while
scaffolding shrouded in burlap surrounds the main axle. [...]

In the absence of official information, residents of Bluewaters Island have
been left guessing. Some say the Ain started vibrating loudly during the
five months it was operational. Others claim the giant structure shook the
ground when it turned. One shopkeeper said the shaking shattered
windows. Others fear the foundation has been compromised. All spoke on the
condition of anonymity, fearing repercussions from the UAE’s image-conscious
authorities. [...]

Germany’s Technical Inspection Association, or TUV, confirmed that it was
involved in the Ain’s construction but had withdrawn its certification for
the structure. The group, which tests and provides independent safety
certifications for a variety of technical systems, gave no further comment,
saying it was bound by a nondisclosure agreement. The Ain’s media office did
not respond to requests for comment.

https://www.washingtonpost.com/world/2023/07/09/ain-dubai-wheel-real-estate/

------------------------------

Date: Thu, 6 Jul 2023 06:30:10 -0600
From: Matthew Kruk <mkr...@gmail.com>
Subject: Suncor swaps out laptops after cybersecurity incident as energy
sector takes stock of risks (CBC)

https://www.cbc.ca/news/canada/calgary/suncor-cybersecurity-incident-energy-sector-1.6898118

Suncor is replacing employee computers after a cybersecurity incident last
week shut down debit and credit processing at Petro-Canada gas stations
across the country, among a series of other security measures at the
Calgary-based company.

An internal communication dated July 3, viewed by CBC News, says the
company will replace desktop and laptop computers in waves to ensure the
devices are safe to use, starting with "a small number of employees and
contractors aligned with business criticality."

It's not clear from the memo what the scope of the computer recall is or
what departments were affected, but one expert said that if the recall is
extensive, it would be an indication of a serious situation.

------------------------------

Date: Thu, 6 Jul 2023 20:35:12 -0600
From: Matthew Kruk <mkr...@gmail.com>
Subject: Unauthorized party' obtained Petro-Points members' contact
information in IT breach, company says (CBC)

https://www.cbc.ca/news/canada/calgary/petro-points-suncor-it-breach-1.6899274

An unauthorized party obtained Petro-Points members' basic contact
information in a cybersecurity incident that happened roughly two weeks ago,
the company said Thursday.

In an email to customers, Petro-Canada said it believes the information was
limited to customers' names and the information they "may have provided"
since joining the program, specifically their mailing and email addresses,
phone numbers and dates of birth.

It's now warning customers to watch out for unusual emails and messages and
to "confirm that any request to link, download, call someone or provide
personal information is legitimate."

------------------------------

Date: Sat, 8 Jul 2023 09:55:15 -0400
From: Gabe Goldberg <ga...@gabegold.com>
Subject: One Careless Act of War Could Destroy All Satellites in
Just 40 Years (ScienceAlert)

On one particular day in 2021, astronauts and cosmonauts aboard the ISS must
have felt a pin-prick of fear and uncertainty. On November 15th of that
year, Russia fired an anti-satellite missile at one of its own defunct
military satellites, Tselina-D.

The target weighed about 1,750 kilograms, and when the missile struck its
target, the satellite exploded into a cloud of hazardous debris.

NASA woke the crew on the International Space Station in the middle of the
night and told them to take precautions and prepare for a possible
impact. The Chinese space station Tiangong was also in danger, and multiple
countries and space agencies condemned Russia's foolhardy behavior.

But there was no way to contain the debris.

https://www.sciencealert.com/one-careless-act-of-war-could-destroy-all-satell
ites-in-just-40-years

------------------------------

Date: Wed, 5 Jul 2023 20:27:57 -0400
From: Gabe Goldberg <ga...@gabegold.com>
Subject: EV Charger Hacking Poses a Catastrophic Risk (WiReD)

Vulnerabilities in electric vehicle charging stations and a lack of broad
standards threaten drivers—and the power grid.

https://www.wired.com/story/electric-vehicle-charging-station-hacks

------------------------------

Date: Thu, 6 Jul 2023 00:22:54 +0000
From: Douglas Lucas <d...@riseup.net>
Subject: Georgia won't, can't certify voting update addressing Halderman
report

Today the BradBlog.com, run for two decades and counting by journalist Brad
Friedman of the syndicated AM/FM radio show the BradCast, published on July
5 my new investigative article titled ...

Exclusive: Georgia Secretary of State Has Failed to Certify Urgent,
CISA-Recommended Voting Software Update

and subtitled ...

Critics charge state laws block him from doing so, even if he wanted to...

Here's the hyperlink: https://bradblog.com/?p=14711

In short, Georgia's Secretary of State Brad Raffensperger has not contracted
with a certification agent (typically a VSTL or voting system test
laboratory) to get an examination done for Dominion Democracy Suite
5.17. Other evidence similarly shows Raffensperger isn't moving, and cannot
move, on the 5.17 software version. According to Univ Michigan computer
science professor J. Alex Halderman -- whose report on the matter was
unsealed by a federal judge last month -- 5.17 purportedly addresses the
flaws he uncovered in version 5.5-A. That older 5.5-A version is presumably
what we'd find in place if we wheeled out the voting computers presently
locked away in Georgia warehouses and closets and booted them up. It's the
same defective version currently slated to be used for Election Day 2024,
since Raffensperger says he won't update till at least 2025. With how long
these issues have been raised, Raffensperger is slower at patching computers
than the U.S.'s whole involvement in World War II. Given the Coffee County
breach (see my last article) and Halderman's report, the vulns of 5.5-A are
probably widely spread by now, putting a Nov 2024 bullseye on Georgia's back
unless they update or, say, switch to hand-marked paper ballots tabulated by
scanners checked through mandatory, robust Prof Stark-style risk-limiting
audits.

RISKS? Lying State Secretary spokesperson overseeing an opaque department,
proprietary software (no way to really know if 5.17 actually does mend 5.5-A
to any impressive degree), physical breaches leading to exact copies being
uploaded to secret sites for restricted audiences seeking partisan and/or
pecuniary gain (Coffee County), and voters who typically only care about
earn their I Voted stickers on Election Day -- with gale-force screeching
about it, -- yet ignore election mechanics the 3-plus other years of each
presidential cycle, because, it is said, thinking too hard, caring too much,
is uncool, especially when there's so much good TV lately and we work so we
deserve to just be happy...

------------------------------

From: Matthew Kruk <mkr...@gmail.com>
Date: Thu, 6 Jul 2023 06:23:23 -0600
Subject: India's religious chatbots condone violence using the voice of god
(CBC)

https://www.cbc.ca/news/world/india-religious-chatbots-1.6896628

Experts warn of potential dangers as new chatbots use AI to interpret Hindu
scripture

------------------------------

Date: Sat, 1 Jul 2023 19:28:21 -0400
From: DrM <not...@mindspring.com>
Subject: Re: Three Companies Supplied Fake Comments to FCC (R-33.70+)

What a mess there, with no ability to renew or get new licenses for nearly A
MONTH. Unclear what happened, whether it was part of the larger attack on
U.S. government systems. I have a bunch of the notices that were posted.
Below is one about the resumption of processing Amateur Radio licenses. The
public notice from the FCC was a first, I think -- they had to issue a
waiver where broadcasting with an expired license was allowed. You can see
it at the FCC.gov link. Even these FCC notices are rather vague about what
was going on. Likely we'll never get the full story.

You're welcome to post both of these to Risks, with modest attribution to me
(Rebecca Mercuri sent...) but I didn't write any of it (though I was
affected, as I had some students who were and still are waiting to receive
their licenses).

Rebecca M.

- - - -

> Date: Thu, Jun 22, 2023 at 12:00 PM
> From: *ARRL Web site* <membe...@arrl.org>
> Subject: ARLB013 FCC ULS Reopened, Except Electronic Batch Filing System

SB QST @ ARL $ARLB013
ARLB013 FCC ULS Reopened, Except Electronic Batch Filing System

ZCZC AG13
QST de W1AW
ARRL Bulletin 13  ARLB013
>From ARRL Headquarters
Newington CT  June 22, 2023
To all radio amateurs

SB QST ARL ARLB013
ARLB013 FCC ULS Reopened, Except Electronic Batch Filing System

On Wednesday morning, June 21, 2023, the FCC had reopened the
Universal Licensing System (ULS) and supporting systems, according
to an email distributed to VEC organizations. However, as of 4:00 PM
on Wednesday, the Electronic Batch Filing (EBF) system, used by VEC
organizations for filing exam sessions, individual applications, and
club license applications, was still not available as promised.
Unfortunately, this means applications for new and upgraded
licenses, and individual and club license filings still cannot be
uploaded in the system for issuance.

When the EBF system becomes available, the Commission is requesting
VECs to limit submissions into the filing system. In an email sent
by the FCC, all EBF filers were asked to adhere to a restricted
upload schedule in order to keep the EBF system stable and to avoid
any potential technical problems. The FCC will be monitoring to
ensure the EBF system is stable during this reopening period. If
they assess that the upload volume is too high, they will send out
another notice with directions to reduce the amount of uploads per
hour.

ARRL VEC will comply with the FCC directive, limiting our
transmissions but sending as many backlogged sessions as possible
without overloading their system. The files will be submitted to the
FCC in the order in which they were received, starting with the
files from Monday, June 12, and moving forward from there. ARRL VEC
will begin submitting the backlogged applications as soon as the EBF
system becomes available, and assuming all FCC systems remain
stable.

In an FCC notice published on June 21, 2023 (please see,
https://www.fcc.gov/document/uls-tcns-e-106-and-asr-available), the
Commission provided a deadline extension for filings in the ULS and the
Antenna Structure Registration (ASR) system, explaining, "Because parties
could not make electronic filings or view the contents of the affected
systems while they were unavailable, we are extending the deadlines for all
regulatory filings that were due in the affected systems between June 9,
2023, and June 29, 2023, until Friday, June 30, 2023.

"We note that we have provided for a longer extension for these filings than
initially contemplated in the June 13 Public Notice in anticipation of high
traffic volumes on these systems in the coming days. In that regard, we
encourage filers to consider deferring discretionary filings this week, and
we encourage filers preparing large submissions to coordinate in advance
with [the] staff of the Bureaus."

- - - -

Also from ARRL:

SB QST @ ARL $ARLB014
ARLB014 FCC ULS System Restored

ZCZC AG14
QST de W1AW
ARRL Bulletin 14  ARLB014
> From ARRL Headquarters
Newington CT  June 27, 2023
To all radio amateurs

SB QST ARL ARLB014
ARLB014 FCC ULS System Restored

The FCC Universal Licensing System (ULS) has resumed operations,
including the Electronic Batch Filing system (EBF).

As of June 27, 2023, all systems have been reported to be working.
However, visitors to the website will see a message referring them
to Public Notice DA 23-529 for additional information and guidance
on filing deadline extensions.

The systems were first reported unavailable on June 9, 2023. On
Friday afternoon, June 23, the EBF system was restored. All VEC
organizations use that system for filing exam sessions, individual
applications, and club license applications. ARRL VEC staff worked
late into Friday night to ensure all backlogged sessions and
application files were transmitted to the FCC before the weekend.
Approximately 350 backlogged files were successfully submitted to
and processed by the FCC before the system's normal shutdown at 8
PM.

ARRL is still monitoring the ULS system, and any further updates
will be available at ARRL News.

------------------------------

Date: Mon, 3 Jul 2023 09:14:470100
From: Mike Scott <usen...@scottsonline.org.uk>
Subject: Re: The cleaner did it: an uncool act. (RISKS-33.74)

Dare one say "single point of failure" and ask why the entire set of
research materials were all stored in one place? Surely dividing between
separate freezers in different buildings (or even towns) would have been in
order for something so apparently vital.

------------------------------

Date: Mon, 3 Jul 2023 12:00:55 +0300
From: Amos Shapir <amo...@gmail.com>
Subject: Re: Is America Ready For AI-Powered Politics? (Alexander,
RISKS-33.74)

> "How long before we have a large body of correspondence with no human
> involvement or oversight of any sort?"

Not only that, but the output of such correspondence is posted back into the
same spaces which serve as training fodder for the next issue of AI
programs.

As any sound technician knows, a positive feedback which occurs in a sound
system enhances itself exponentially until very quickly the
feedback-generated noise drowns out other sounds, making the system
unusable.

------------------------------

Date: Sat, 1 Jul 2023 11:11:11 -0800
From: RISKS-...@csl.sri.com
Subject: Abridged info on RISKS (comp.risks)

The ACM RISKS Forum is a MODERATED digest. Its Usenet manifestation is
comp.risks, the feed for which is donated by panix.com as of June 2011.
=> SUBSCRIPTIONS: The mailman Web interface can be used directly to
subscribe and unsubscribe:
http://mls.csl.sri.com/mailman/listinfo/risks

=> SUBMISSIONS: to ri...@CSL.sri.com with meaningful SUBJECT: line that
includes the string `notsp'. Otherwise your message may not be read.
*** This attention-string has never changed, but might if spammers use it.
=> SPAM challenge-responses will not be honored. Instead, use an alternative
address from which you never send mail where the address becomes public!
=> The complete INFO file (submissions, default disclaimers, archive sites,
copyright policy, etc.) has moved to the ftp.sri.com site:
<risksinfo.html>.
*** Contributors are assumed to have read the full info file for guidelines!

=> OFFICIAL ARCHIVES: http://www.risks.org takes you to Lindsay Marshall's
searchable html archive at newcastle:
http://catless.ncl.ac.uk/Risks/VL.IS --> VoLume, ISsue.
Also, ftp://ftp.sri.com/risks for the current volume/previous directories
or ftp://ftp.sri.com/VL/risks-VL.IS for previous VoLume
If none of those work for you, the most recent issue is always at
http://www.csl.sri.com/users/risko/risks.txt, and index at /risks-33.00
ALTERNATIVE ARCHIVES: http://seclists.org/risks/ (only since mid-2001)
*** NOTE: If a cited URL fails, we do not try to update them. Try
browsing on the keywords in the subject line or cited article leads.
Apologies for what Office365 and SafeLinks may have done to URLs.
==> Special Offer to Join ACM for readers of the ACM RISKS Forum:
<http://www.acm.org/joinacm1>

------------------------------

End of RISKS-FORUM Digest 33.75
************************

0 new messages