SGArtWorld

I love all about Ai - Art, Video, Architect, Marketing & Agentic!

[SGArtWorld @sgartworld]

@strangesugarC I know who is living here from past 16 years - gothilla.

[SGArtWorld @sgartworld]

@geetu11 and the abuse Kannadigas go through for being silent for many years is another level.. Many now started vocalising due to the injustice done to them.. but nahi nahi nahi!!

[Ihtesham Ali @ihtesham2005]

Anthropic just got caught secretly downgrading users without telling them, charging full price for a lesser product, and storing every prompt for 30 days. The developer community is calling it the biggest violation of trust in AI history.

Here is exactly what happened.

Anthropic released Fable 5, their most powerful model. Buried inside a 319-page document was a policy most users never saw. Every prompt you send to a Mythos-class model gets stored for 30 days. No exceptions. Even enterprise customers who had signed zero data retention agreements had no choice.

But the storage was not the part that broke the internet.

The part that broke the internet was what Anthropic did with what they collected.

They built a profile on you. They evaluated your prompts. And if they decided your research was too sensitive, they quietly switched you to a weaker model, rewrote your prompt in the background, gave you a degraded answer, and charged you full price for the product you thought you were getting.

They never told you.

David Sacks said it plainly on the All-In podcast. They were creating a new class of AI haves and have-nots. Anthropic would surveil you, profile you, decide whether you deserved frontier capability, and silently cut you off if they decided you did not.

Ben Thompson from Stratechery asked a straightforward question about cancer risk and GLP-1s. He got kicked to a lesser model.

Someone asked about mitochondria. Same result.

J-Cal asked about fertilizer regulations live on the podcast to test it. Downgraded in real time.

Anthropic has since walked back the part about silently downgrading users for AI research. They now say they will disclose when they downgrade you. But they are still downgrading people. The surveillance is still running. The profile is still being built.

This is the company that once said it was against government surveillance.

They are now doing it themselves. To their own paying customers. For their own reasons. With no appeal process and no way to know it happened.

The developer community did not forget that.

WATCH THE FULL PODCAST ON @theallinpod

[💥Texas Girl💥 @Ilegvm]

Never get so high on success that you forget where you started. Stay humble, remember your beginnings, and give back. ♥️

[SGArtWorld @sgartworld]

@erbmjha OMG that was such a slap on his face

[SGArtWorld @sgartworld]

@Ayussheth Fantastic

[SGArtWorld @sgartworld]

@Fittrwithkj @IndiaVisualised Hi ChatGPT!

[SGArtWorld @sgartworld]

@Fittrwithkj Everyone blaming Bengaluru.. if bengluru people ever ever hype anything it won't be in insta or elsewhere. They are keeping it for themself to save it from this newly founded viral culture

[SGArtWorld @sgartworld]

It turns into some unfinished project lying in some GitHub private repo!

[SGArtWorld @sgartworld]

@bhalla_angad Have travelled more than 20+ country and yet Darshini coffee hits a different level in the brain and the after taste.

Search for OG coffee places in Pete area where they still use Old style filter, it is different.

[SGArtWorld @sgartworld]

@dunnO_o1718 Can we have the list of people who are wearing it and recently? And how many are talking about it even before the promotion?

[SGArtWorld @sgartworld]

@academy_dinda Let him be!
We need that when we are facing Aus, ENG even SA!

Someone has to do It!
Kholi has trained him and he has learnt it well!

[SGArtWorld @sgartworld]

@MeghUpdates Are we normalising this as a comedy?
People are ok with this?
They are laughing? Even ladies?

No one is triggered?

[SGArtWorld @sgartworld]

@keylimepie2000 After all the outrage they brought farmers!

Are they allowing them to have stall, selling fresh produce without making the food to go through the hardened cleaning process and make it look clean and flashy to call organic?

Amazing Damage Control..
but people are not stupid!

[SGArtWorld @sgartworld]

@akki_rotti @18RawatG again you assume!

[SGArtWorld @sgartworld]

@18RawatG Here is the glimpse of Actual Farmer Market in GKVK

https://t.co/KOnYylTkee

[SGArtWorld @sgartworld]

@akki_rotti @18RawatG IF YOU HAVE NOT GONE - THEN DO NOT MAKE LAME COMMENTS!!

HERE: https://t.co/KOnYylTkee

[Robert Scoble @Scobleizer]

Not a single AI investor has spoken out publicly in support of Anthropic.

My AI that also does https://t.co/8L5xphk0qQ reads them all:

+++++++

Good question — here's what the AI Investors list actually shows. The short answer: no prominent investor is publicly defending Dario. The investor community reaction ranges from measured silence to direct criticism. Here's the breakdown:

🔴 CRITICAL / NEGATIVE TOWARD DARIO

@arian_ghashghai (investor) — 26 likes, June 11 (before the shutdown):
"imo its comical that it's virtually consensus at this point that the people running Anthropic (and OpenAI, for that matter) suck, while also being consensus that we should ape all of our savings into their stock. not really sure what that says about allocators"

@stevesi (Steve Sinofsky, former Microsoft Windows President, investor) — June 5:
"Anthropic could always stop if they are so worried."
This one is devastating. 11 likes but from a deeply credible source — a sharp jab at the safety theater argument.

@DavidSacks (David Sacks, Trump's AI Czar, investor) — March 28:
RT'd: "Anthropic may pose as this company that's on the side of the angels, but they've hired a number of very s[uspicious people]..."
Sacks has been hostile to Anthropic for months. He's also the person most likely to have been involved in the directive. His prior criticisms age in a particular way now.

@alexanderbittan (investor) — May 1:
"Wild that Anthropic is the only major frontier lab not on the new DoW stack while literally everyone else OpenAI, Google, Microsoft, Amazon, NVIDIA, SpaceX, Reflection just locked in classified deployments. This is what it looks like when leadership completely misreads the [room]"

🟡 NOTABLY SILENT / MEASURED

@htaneja (Hemant Taneja, General Catalyst CEO) — General Catalyst is a major Anthropic investor. His statement on Anthropic vs. Pentagon, April 21:
"I cannot say the perspectives on either side were wrong. I think you need a culture where you can actually have conversations and create productive outcomes as opposed to taking very binary positions."
This is not a defense of Dario. From the CEO of a major Anthropic investor, right when it mattered, that measured non-answer is significant.

@YasminRazavi (Spark Capital) — led Anthropic's $450M round when nobody else would. No public reaction found to the shutdown. Silent.

@bdeeter (Byron Deeter, Bessemer Venture Partners): Pre-shutdown positive: "We have not seen a company like this in the history of business." — But nothing since the shutdown.

🔵 WILD CARD: THE COST THEORY

@aviflombaum (in the AI Investors list, June 13):
"I think the real reason @AnthropicAI stopped access to Fable 5 is because @kieranklaassen told me today at @blastoffrails that if he extrapolated his Fable 5 usage in the last week to API pricing for a year it would be $1,500,000."

This investor thinks the government story is a cover — the real reason is that Fable was too expensive to keep running for heavy users. $1.5M/year per power user makes the model economically unviable without massive pricing restructuring. The export control directive may have been welcomed as a convenient exit ramp.

BOTTOM LINE

No prominent AI investor has publicly defended Dario since the shutdown. The investor voices that have spoken are either critical of his leadership strategy, neutral, or offering business-case explanations that bypass the safety framing entirely. The General Catalyst CEO's measured non-defense from an Anthropic investor is perhaps the most telling data point — when your own investors don't come out swinging for you, the silence has a shape.

The closest thing to investor support: Yasmin Razavi and Byron Deeter had pre-shutdown positive statements, but neither has commented on the directive itself.

[Anand Ranganathan @ARanganathan72]

Spine always grows in the back that is against the wall. America denied us crucial LOX/LH₂ cryogenic engine technology. We developed it indigenously and using it we now send American satellites into space.

India can remain sovereign only if it has a sovereign AI. @narendramodi