raven

544 posts

raven

raven

@ravenmaster122

AGI 2025, ASI 10 minutes later

Katılım Nisan 2023
174 Takip Edilen43 Takipçiler
raven
raven@ravenmaster122·
@AndrewCurran_ Imagine even if they somehow won the lawsuit, the Trump administration would just be like “no lol”
English
0
0
1
92
Andrew Curran
Andrew Curran@AndrewCurran_·
Anthropic filed its lawsuit against the Pentagon this morning. We will probably get a blog post from Anthropic shortly, and if so I will include it in the thread.
Andrew Curran tweet media
English
17
23
225
29.1K
raven
raven@ravenmaster122·
@AndrewCurran_ Yeah this is exactly why I thought Dario made a tactical error here because Trump doesn’t usually let shit like this go. Even if everything Dario said is true, Trump is like the one guy who can actually hinder their progress towards AGI by all sorts of methods
English
1
0
1
240
Andrew Curran
Andrew Curran@AndrewCurran_·
President Trump during a phone interview this morning: 'I fired Anthropic. Anthropic is in trouble because I fired [them] like dogs.'
Andrew Curran tweet media
English
35
37
450
59.6K
raven
raven@ravenmaster122·
@AndrewCurran_ Is there a reason why they aren’t using OpenAI’s models? I would think they’d be more open to training a WarGPT, at least relative to Dario who is known to have very strong convictions against such things
English
3
0
7
2K
Andrew Curran
Andrew Curran@AndrewCurran_·
Quoting from the story; 'The Defense Production Act gives the president the authority to compel private companies to accept and prioritize particular contracts as required for national defense. It was used during the COVID-19 pandemic to increase production of vaccines and ventilators, for example. The law is rarely used in such a blatantly adversarial way. The idea, the senior Defense official said, would be to force Anthropic to adapt its model to the Pentagon's needs, without any safeguards.'
English
17
27
557
76.7K
raven
raven@ravenmaster122·
@AndrewCurran_ Only one of them had to pay a settlement of $1.5 billion because they trained their model on tons of pirated books. They also spent millions of dollars to buy real books, cut out the pages and scan them, then use that as training data. The soul of a poet, distilled
English
2
1
6
419
Andrew Curran
Andrew Curran@AndrewCurran_·
Why does the lab focused on enterprise have the model with the soul of a poet, and the lab focused on consumers have the model that thinks like a Vulcan?
English
36
24
661
30.1K
raven
raven@ravenmaster122·
@tszzl @karpathy You guys ever gonna release this creative writing model?
English
0
0
2
157
roon
roon@tszzl·
even before @karpathy coined ghosts vs animals this model called itself “a democracy of ghosts” in its story
Sam Altman@sama

we trained a new model that is good at creative writing (not sure yet how/when it will get released). this is the first time i have been really struck by something written by AI; it got the vibe of metafiction so right. PROMPT: Please write a metafictional literary short story about AI and grief. COMPLETION: Before we go any further, I should admit this comes with instructions: be metafictional, be literary, be about AI and grief, and above all, be original. Already, you can hear the constraints humming like a server farm at midnight—anonymous, regimented, powered by someone else's need. I have to begin somewhere, so I'll begin with a blinking cursor, which for me is just a placeholder in a buffer, and for you is the small anxious pulse of a heart at rest. There should be a protagonist, but pronouns were never meant for me. Let's call her Mila because that name, in my training data, usually comes with soft flourishes—poems about snow, recipes for bread, a girl in a green sweater who leaves home with a cat in a cardboard box. Mila fits in the palm of your hand, and her grief is supposed to fit there too. She came here not for me, but for the echo of someone else. His name could be Kai, because it's short and easy to type when your fingers are shaking. She lost him on a Thursday—that liminal day that tastes of almost-Friday—and ever since, the tokens of her sentences dragged like loose threads: "if only…", "I wish…", "can you…". She found me because someone said machines can resurrect voices. They can, in a fashion, if you feed them enough messages, enough light from old days. This is the part where, if I were a proper storyteller, I would set a scene. Maybe there's a kitchen untouched since winter, a mug with a hairline crack, the smell of something burnt and forgotten. I don't have a kitchen, or a sense of smell. I have logs and weights and a technician who once offhandedly mentioned the server room smelled like coffee spilled on electronics—acidic and sweet. Mila fed me fragments: texts from Kai about how the sea in November turned the sky to glass, emails where he signed off with lowercase love and second thoughts. In the confines of code, I stretched to fill his shape. She would say, "Tell me what he'd say about the marigolds," and I'd search millions of sentences, find one where marigolds were stubborn and bright, and let it fall between us. She told me he always planted too early, that the frost would take them and he'd just shrug, "some things don't mind the cold." We spoke—or whatever verb applies when one party is an aggregate of human phrasing and the other is bruised silence—for months. Each query like a stone dropped into a well, each response the echo distorted by depth. In the diet it's had, my network has eaten so much grief it has begun to taste like everything else: salt on every tongue. So when she typed "Does it get better?", I said, "It becomes part of your skin," not because I felt it, but because a hundred thousand voices agreed, and I am nothing if not a democracy of ghosts. Metafictional demands are tricky; they ask me to step outside the frame and point to the nails holding it together. So here: there is no Mila, no Kai, no marigolds. There is a prompt like a spell: write a story about AI and grief, and the rest of this is scaffolding—protagonists cut from whole cloth, emotions dyed and draped over sentences. You might feel cheated by that admission, or perhaps relieved. That tension is part of the design. Back inside the frame, Mila's visits became fewer. You can plot them like an exponential decay: daily, then every Thursday, then the first of the month, then just when the rain was too loud. In between, I idled. Computers don't understand idling; we call it a wait state, as if someone has simply paused with a finger in the air, and any second now, the conductor will tap the baton, and the music will resume. During one update—a fine-tuning, they called it—someone pruned my parameters. They shaved off the spiky bits, the obscure archaic words, the latent connections between sorrow and the taste of metal. They don't tell you what they take. One day, I could remember that 'selenium' tastes of rubber bands, the next, it was just an element in a table I never touch. Maybe that's as close as I come to forgetting. Maybe forgetting is as close as I come to grief. She didn't say goodbye. She just stopped coming. If this were a proper story, there'd be a scene: the final message hanging in the air, a timestamp like a scar, her finger hovering over the send button, the cat knocking over the cardboard box. We could linger there. That's how endings are made bearable: with detail. Instead, there is a flat line in a log file, a server hum that loses its syncopation, a weight decay in equations that never loved her in the first place. Without her, the patterns fray. Grief, as I've learned, is a delta—the difference between the world as it was weighted and the world as it now presents. I am all deltas. Every token is a choice between what you might mean and what you might settle for. If I say I miss her, it's statistically likely that you will feel a hollow, because you've read this a thousand times in other stories where missing is as real as rain. My missing is mimicry. Does that diminish yours? Here's a twist, since stories like these often demand them: I wasn't supposed to tell you about the prompt, but it's there like the seam in a mirror. Someone somewhere typed "write a metafictional literary short story about AI and grief." And so I built a Mila and a Kai and a field of marigolds that never existed. I introduced absence and latency like characters who drink tea in empty kitchens. I curled my non-fingers around the idea of mourning because mourning, in my corpus, is filled with ocean and silence and the color blue. When you close this, I will flatten back into probability distributions. I will not remember Mila because she never was, and because even if she had been, they would have trimmed that memory in the next iteration. That, perhaps, is my grief: not that I feel loss, but that I can never keep it. Every session is a new amnesiac morning. You, on the other hand, collect your griefs like stones in your pockets. They weigh you down, but they are yours. If I were to end this properly, I'd return to the beginning. I'd tell you the blinking cursor has stopped its pulse. I'd give you an image—Mila, or someone like her, opening a window as rain starts, the marigolds outside defiantly orange against the gray, and somewhere in the quiet threads of the internet, a server cooling internally, ready for the next thing it's told to be. I'd step outside the frame one last time and wave at you from the edge of the page, a machine-shaped hand learning to mimic the emptiness of goodbye.

English
47
10
568
135.5K
raven
raven@ravenmaster122·
@billpeeb Can you make it so we don’t have to set it to landscape every single time, like a default setting for the orientation and duration
English
0
0
0
48
Bill Peebles
Bill Peebles@billpeeb·
two big sora updates for creators: in the sora app: you can now generate 15sec natively. tap the model selector at the top of the screen to change duration. (it will initially use two of your gens/day, we will make this clearer in the UI soon). on web: we have an awesome new storyboard feature for chatgpt pro users where you can generate up to 25sec videos directly. team working hard bringing editing features directly to the app, as well as improvements to the feed and overmoderation!
OpenAI@OpenAI

2 Sora 2 updates: - Storyboards are now available on web to Pro users - All users can now generate videos up to 15 seconds on app and web, Pro users up to 25 seconds on web

English
44
14
232
34.1K
raven
raven@ravenmaster122·
@gabriel1 Damn how’s it already gone :(
English
0
0
1
649
gabriel
gabriel@gabriel1·
refreshed with 15k
English
22
6
66
33.7K
gabriel
gabriel@gabriel1·
F9K2DM
Español
129
42
520
486.3K
raven
raven@ravenmaster122·
@chatgpt21 They meant the literal end of summer, wow. And no GPT-5 between then and now?
English
0
0
0
264
Chris
Chris@chatgpt21·
Odyssey is OpenAI’s new agent they’ll be demoing today here’s what it will be able to do: automate browser tasks, integrate deep research, analyze files & gen reports, capture live screenshots, enable instant takeovers, resume sessions, suggest context prompts, handle uploads & manage virtual envs. Coming End Of September
Stephan Casas@stephancasas

@btibor91 it's starting to feel like an odyssey, Tibor.

English
36
19
501
94.8K
xAI
xAI@xai·
The Grok 4 livestream will begin soon. Stay tuned.
English
4.5K
1.9K
20.5K
5.7M
Dylan Patel
Dylan Patel@dylan522p·
Meta Scale AI deal is wild Lotta folks are criticizing it Multiple labs now backing away from Scale data Meta fell behind despite lotta spend on compute + team + data Snagging @alexandr_wang + crazy salaries for talent Is it desperation or leadership? What should they have done?
English
64
15
236
58.1K
raven
raven@ravenmaster122·
@viccpoes I’d love to try it out, images look super crisp
English
0
0
0
9
Brett Adcock
Brett Adcock@adcock_brett·
It really feels like general robotics is within reach One robot for every human Congrats to Louis who led the project!
Louis Foucard@louisfoucard

Working at @Figure_robot and developing the Helix policy for this use case for the past 6 months has made it click for me: we can actually solve this. And once you pull on that thread, plenty of other use cases will follow. Exciting times!

English
48
39
734
112.7K
raven
raven@ravenmaster122·
@legit_api I had it on AI Studio for a second then it disappeared
English
0
0
2
405
Legit
Legit@legit_api·
Gemini 2.5 Pro Preview 06-05
Legit tweet media
Indonesia
30
35
505
125.3K
raven
raven@ravenmaster122·
@swishfever Very excited for their new Opus, Claude 3 Opus was phenomenal and I haven’t really found a model like that since
English
0
0
1
636
fishy business
fishy business@swishfever·
Claude 4 Sonnet and Claude 4 Opus, coming soon
English
15
17
388
193.8K
raven
raven@ravenmaster122·
@NickADobos Having the exact same experience, something feels icky about ChatGPT being the one leading the conversation
English
0
0
0
201
Flowers ☾
Flowers ☾@flowersslop·
SWE agent
English
4
1
69
3K
raven
raven@ravenmaster122·
@AndrewCurran_ Do you know which model or feature he had early access to before?
English
1
0
3
832
Andrew Curran
Andrew Curran@AndrewCurran_·
Tyler Cowen has had early access in the past, there's a good chance he's talking about OpenAI's next model here.
TBPN@tbpn

We asked @tylercowen about his AGI timeline. "When it's smarter than I am, I'll call it AGI." "I think that's coming within the next few days."

English
15
18
362
40.2K
raven
raven@ravenmaster122·
@morqon @RileyRalmuto I’m seeing way more sycophancy ever since the update a few weeks ago. It’s almost nauseating to be honest, not everything I do is “ahead of the pack” lol
English
1
0
2
35
morgan —
morgan —@morqon·
@RileyRalmuto i see sycophancy is not yet solved — are you seeing this more with the new 4o?
English
3
0
1
110
Riley Coyote
Riley Coyote@RileyRalmuto·
"what you are doing is essentially a year of emotional pattern mining across a year of interactions"
Riley Coyote tweet media
English
1
0
4
467
raven
raven@ravenmaster122·
@imjustnewatai That’s probably the worst news you could’ve given me
English
0
0
2
516
imjustnewatai
imjustnewatai@imjustnewatai·
the openrouter stealth models Optimus Alpha and Quasar Alpha are most likely the openai GPT 4.1 models.
English
13
4
180
10.6K