Support NeoGAF

[cormack12]

Be easier to just let us earn credits to buy graphics cards or memory

 

[Goalus]

I use CoPilot in VSCode pretty much every day. It's a great assistance tool. I like being able to switch between OpenAi and Anthropic models pretty much on the fly.

I use it almost daily in Edge. Why would I install a separate app when I can just click an icon in the Edge address bar?

 

[NickFire]

A 200 a month sub that makes you still watch ads is bananas.

 

[ReBurn]

I use it almost daily in Edge. Why would I install a separate app when I can just click an icon in the Edge address bar?

I don't write software in Edge, but I do in VSCode. That's why I use it in VSCode. You can use it in whatever app you want to.

 

[ReBurn]

Could you elaborate more on what you mean?

I subscribe to GitHub CoPilot and you get to pick the models you use when you run prompts and perform agentic tasks. I use GPT-5 mini for very basic tasks and I like to use Claude Sonnet 4.5 and GPT-5 for more complex tasks.

 

[Goalus]

I don't write software in Edge, but I do in VSCode. That's why I use it in VSCode. You can use it in whatever app you want to.

I wasn't talking about VS Code.
I just quoted you because you mentioned Copilot.

I was talking about the ChatGPT app. I don't need it since there is a shiny Copilot button in Edge (where I spend 99% of my time on the phone) that does exactly what ChatGPT does.

 

[TheUnicornGuy]

As the world's only Co-pilot user, I'm not affected yet.

You're not alone, I use it as well.

 

[Kenneth Haight]

 

[Rran]

On Reddit, users are not happy with these ads that have popped up seemingly out of nowhere. One user said, "The ads thing is pretty b******t. I might just cancel my Pro subscription."

I'm still trying to figure out what this censored word could possibly be. It's like a puzzle!

"Butthurt" maybe?

 

[Oberstein]

A 200 a month sub that makes you still watch ads is bananas.

Believe me, it could be worse.

(It's Briana White, the voice of Aerith.)

 

[BattleScar]

Just wait until they start integrating the ads into the chatbot responses to hide them better.

 

[Toots]

As Chirac said "promises are only binding to those who believe them".
It is everybody's own fault they believe carpet sellers like altman and musk.
It is exactly like believing Erdogan, that watermelon seller.

 

[Melon Husk]

Time to install a local llm. Let me just buy a few RAM sticks... oh.

 

[BennyBlanco]

 

[falconhoof]

Here are our principles. Most importantly, we will not YET accept money to influence the answer ChatGPT gives you, and we keep your conversations private from advertisers FOR THE TIME BEING.

 

[ZehDon]

Speed running the enshitification process.

"Sure, here's some information related to your question.

But first, let me tell you about today's sponsor: NordVPN…"

 

[Forsete]

Hopefully this is the beginning of the end of "AI".

How many trillions invested so far?
The fallout will be magnificent. Countries could crumble.

 

[Big-G]

Hopefully this is the beginning of the end of "AI".

How many trillions invested so far?
The fallout will be magnificent. Countries could crumble.

AI will stay. The military, Medical, R&D, and major corporations will still use it for a lot of the background stuff, like research, analytics, and data processing. Still, I don't see it being widely adopted in the retail/consumer market for general public use. It seems these AI companies are having a hard time trying to market these products to retail consumers.

 

[Dr Bass]

You know, I've seen this clip over and over since I was a young lad and even back then it struck me as stupid that Lucas felt like Star Wars plots had to echo each other over the generations. But what gets me now is thinking that Lucas' concept of poetry is making things rhyme.

 

[MidGenRefresh]

But I thought they were on a path to achieving AGI. An all-knowing computer god, so why would they need to sell ads for scam mobile games?

 

[SJRB]

Very grim.

 

[Saber]

Very grim.

Every stupid principle in this sheet could be answered with a single phrase.

"For now"

 

[negator2vc]

Very grim.

I am not sure.
Unlike other services for ex. google search or youtube where you have no other choice in AI case we have how many AIs now?

 

[Dirk Benedict]

Very grim.

The man is a pathological liar at this point.

 

[archangelmorph]

Best way to kill consumer loyalty before they've even started getting going.

Utterly crazy and just lazy....

They could do this soo much more subtly/subversively...:

"Here's my answer to your question on XYZ... <blah blah>... If you're interested in finding the top ten providers in this space then I'm happy to provide some recommendations?"

"Of course! Here's a list of suggestions according to ABC sources... Also here's a list of sponsored suggestions that you might prefer to check out instead..."

Then just charge companies through the nose, ass and ears to pay to rank in these lists.

EDIT:

I wouldn't care, something like this sets the foundations for true, agentic commerce which will be their biggest cash cow if they can pull their finger out and work towards it...:

"Since you're looking for information on X would you like me to recommend some product suggestions?"

"I can purchase then for you too if you like? Ok let's authenticate against your account... <federated auth style agentic commerce auth handshake w/ your amazon account>... ok your default selected delivery address is X... Let me know if you're happy with this or if you have an alternative delivery address you'll like this sent to?... Ok are you happy for me to make this payment? Ok done... An email has been sent and your product should arrive in 2 days. I can put a reminder in your calendar if you like?"

 

[near]

How is Grok doing these days? It's almost time to delete ChatGPT.

 

[falconhoof]

Remember when Google used to send you search results based on best match?

Then it added very clear side bar ads that were boxed and labelled.

The it put ads in the search results but kept them clearly labelled.

Then it put ads in the same format as search results.

Then it just delivered ads first as search results and actual search results lost all focus.

Their revenue went up with each act, whilst their product got worse.

ChatGPT right now influences its responses. Each prompt conforms to what OpenAI want it to say. Them influencing results based on who pays is not even an imaginative take. Shareholders will demand it and they will oblige.

Google went from "Don't be Evil" to "Fuck it, if it makes money"

 

[Jinzo Prime]

Best way to kill consumer loyalty before they've even started getting going.

Utterly crazy and just lazy....

They could do this soo much more subtly/subversively...:

"Here's my answer to your question on XYZ... <blah blah>... If you're interested in finding the top ten providers in this space then I'm happy to provide some recommendations?"

"Of course! Here's a list of suggestions according to ABC sources... Also here's a list of sponsored suggestions that you might prefer to check out instead..."

Then just charge companies through the nose, ass and ears to pay to rank in these lists.

EDIT:

I wouldn't care, something like this sets the foundations for true, agentic commerce which will be their biggest cash cow if they can pull their finger out and work towards it...:

"Since you're looking for information on X would you like me to recommend some product suggestions?"

"I can purchase then for you too if you like? Ok let's authenticate against your account... <federated auth style agentic commerce auth handshake w/ your amazon account>... ok your default selected delivery address is X... Let me know if you're happy with this or if you have an alternative delivery address you'll like this sent to?... Ok are you happy for me to make this payment? Ok done... An email has been sent and your product should arrive in 2 days. I can put a reminder in your calendar if you like?"

People were crazy for thinking AI was going to somehow give you truthful, objective answers for free. When you have companies like Google and Microsoft involved, it was always going to become a manipulation device controled by the highest bidder.

Just wait until politicians start paying for AI political ads. People thought "Daisy" was shocking, that's nothing compared to what's comimg.

 

[Nintendo's Witch]

Worst LLM by far. The last 5.2 version is the worst.

 

[DKehoe]

 

[falconhoof]

OpenAI could reportedly run out of cash by mid-2027 — analyst paints grim picture after examining the company's finances

The circular economy might spiral into Sam Altman's garrote.

www.tomshardware.com

Given how quickly the evolution of AI has upended technology across the globe and is affecting various markets, it's nigh impossible to accurately predict where anything might be headed. There's no shortage of predictions, ranging from utopia to ultimate doom for established industries. An NYT columnist, however, has one specific bet: OpenAI will be destitute in 18 months in the wake of its AI endeavors.

According to an external report last year, OpenAI was projected to burn through $8 billion in 2025, rising to $40 billion in 2028. Given that the company reportedly predicts profitability by 2030, it's not hard to do the math.

Altman's venture projects spending $1.4 trillion on datacenters. As Sebastian Mallaby, an economist at the Council on Foreign Relations, notes, even if OpenAI rethinks those limerence-influenced promises and "pays for others with its overvalued shares", there's still a financial chasm to cross. Mallaby isn't the only one thinking along these lines, as Bain & Company reported last year that, even with the best outlook, there's at least a $800 billion black hole in the industry.

The financial guru contextualizes the situation adeptly, broadly stating that it's not a matter of whether end-user AI will become technologically entrenched, but rather whether the economics of developing it will make sense in the mid- to long-term.

The analyst points out that in theory, investors would "bridge the gap between the emergence of a great technology and eventual profits", except that many AI companies seem to be burning cash far faster than they can generate income. Mallaby remarks that the newcomers are in a much worse position than "legacy" companies like Microsoft or Meta, given that the old-timers already had money-making businesses before AI came about and can (literally) afford to wait out the necessary period until the clankers deliver the fruits.

According to him, the majority of people are using free services and have no qualms switching to a competitor once their usual bot adds ads or usage limits, a fact corroborated by the myriad options available right now for all sorts of tasks.

He sees this as a temporary problem for AI providers, though, as agentic AI becomes more entrenched in daily people's lives, it'll become harder to switch, as the bots should eventually have all your shopping preferences, aspirations, and emotional profile mapped out —perhaps even better than yourself.

Mallaby does praise OpenAI's CEO Sam Altman's dollar-attracting gravitational field that raised $40 billion in investment, an amount bigger than any other private funding round in history — even more than Saudi Aramco's $30 billion. The difference is that Aramco, along with other IPO'd enterprises, had a business model and profitability, neither of which OpenAI currently enjoys.

The AI financial ouroboros certainly looks poised to eat its own tail, but there's an argument that the ophidian will only lose its newer part. There would be some irony in the AI market losing one or more of the players that started it all.

 

[EverydayBeast]

Why not? - CEO

These mother fudgers are something else.

It's all about the $$