Soneca

2K posts

Soneca banner
Soneca

Soneca

@sousoneca

I comment on threads of people that I don’t know or follow.

Katılım Nisan 2013
103 Takip Edilen160 Takipçiler
Soneca
Soneca@sousoneca·
@levelsio This only shows it is back to 2019 level, right? 2019 wasn’t bad (much less “dead”). Lack of a backlog was never a bottleneck to hire devs. I don’t think AI will scale to infinity and eliminate a backlog of desired features, maintenance, bug fixing and performance improvements
English
0
0
0
15
@levelsio
@levelsio@levelsio·
Tech hiring is dead and it's not coming back I think
@levelsio tweet media
@levelsio@levelsio

Realistically I think most tech jobs are a thing of the past with AI to be honest Right now we're seeing hiring stops everywhere, next will be layoffs I think What will remain is tech founders who build things with entire AI teams which @shl says too and I believe he's right You'd be better off going into construction and building IRL things than coding right now UNLESS you want to start your own tech business where you use AI to build it I think corporations will need 10x to 100x less devs than they have now once they're augmented by AI No idea about timeline and nobody can predict but within next 5 years I think this will slowly happen and again I'm seeing it from Remote OK inb4 "no it's just your site that has a drop bro" ye ye

English
573
618
7K
3.1M
Soneca
Soneca@sousoneca·
@tylercowen Is your AGI definition just answering questions we make? My definition would be, having access to the internet, starting to create accounts, publish blog posts, answer questions on public forums that were not made to it. Your definition of AGI seems to be just pretty good LLM.
English
1
0
12
2.4K
Soneca
Soneca@sousoneca·
@tylercowen Doesn’t alignment, capitalization, and accountability all require individualization? Maybe AI individualization is not possible. Then what?
English
0
0
1
506
Soneca
Soneca@sousoneca·
@tylercowen “Each of those AIs…” How do you individualize an AI? A model? A model running in a specific hardware? A model owned by a human entity? A model running on a hardware owned by a human entity? What about combinations of models and other non-AI software?
English
2
2
5
681
Soneca
Soneca@sousoneca·
@patio11 Started reading more optimistically after your tweets, came out disappointed as always. Maybe that’s because this metafiction style never moved me, not even when written by humans. Also, the grief sentiment felt too stylistic and not sincere to me. Still waiting.
English
0
0
1
113
Patrick McKenzie
Patrick McKenzie@patio11·
(There are giants of many genres who’d be remembered *for that line* specifically if they had penned it first, methinks.)
English
4
1
63
10.3K
Patrick McKenzie
Patrick McKenzie@patio11·
Marking today as the first time I think I read a genuinely moving meditation on grief and loss written by anything other than a human.
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
11
17
462
79.1K
banshee
banshee@_b4nsheee·
@tracklist Claramente eles tão referenciando a Fernanda Montenegro, até citaram central do Brasil
Português
4
0
118
6.7K
Tracklist
Tracklist@tracklist·
E esse vídeo do "Casseta & Planeta" que "previu" a vitória de Fernanda Torres no Globo de Ouro? 😮
Português
66
1.4K
17.6K
431.8K
Soneca
Soneca@sousoneca·
Richarlyson todos sabemos pq alias. Era um baita jogador e muito raçudo (é que Pintado era praticamente a definição de “raçudo”)
Português
0
0
0
81
Soneca
Soneca@sousoneca·
ENTRE TODOS QUE VOCÊ VIU JOGAR NO SEU TIME Melhor bola parada: Rogério Ceni Melhor gringo: tenho leve lembrança do Daryo Pereira como ídolo, mas provavelmente Lugano Mais decisivo: Raí (Palhinha ali perto) Mais raçudo: Pintado Mais talentoso: Kaká Mais xingado: Richarlyson
Drunkeynesian@drunkeynesian

ENTRE TODOS QUE VOCÊ VIU JOGAR NO SEU TIME Melhor bola parada: Craque Neto Melhor gringo: Gamarra e Tevez empatados Mais decisivo: Sheik Mais raçudo: Ralf Mais talentoso: Renato Augusto Mais xingado: Marcelinho Carioca (também poderia entrar em quatro categorias anteriores)

Português
1
0
2
352
Soneca
Soneca@sousoneca·
@EconTalker @tylercowen I asked the econgoat.ai “So, who is the Goat?” and it gave a non-answer saying it depends on the criteria. I insisted and it said it was a tie between Keynes and Smith. I pushed more for a straight single answer and it said Smith. The GPT book is a great idea, btw!
English
0
0
0
148
Soneca
Soneca@sousoneca·
Ninguém pediu, mas vou tentar prever os próximos hits da música brasileira (ou melhor, músicas que eu acho que deveriam ser hits porque são excelentes) A primeira é “Amor e fuleragem” da @biaeosbecks spotify.link/rJ2NidYjeDb
Português
1
0
1
315
Soneca
Soneca@sousoneca·
@paolasiviero se deixariam uma das editoras gigantes lá comprar a outra , se centralizaria muito o mercado e tal. Enfim, o fundador da Random House disse que o nome da editora é justamente porque é muito difícil prever que livro vai estourar. É sempre meio aleatório
Português
0
0
0
13
Soneca
Soneca@sousoneca·
@paolasiviero Se fosse fortemente 2, as editoras saberiam exatamente o que fazer e não haveriam grandes campanhas de livros que acabam não fazendo tanto sucesso. O 2 é mais previsível que 1. E sucesso literário não é nada previsível. Não sei se você acompanham o julgamento nos EUA /
Português
1
0
0
10
Paola Siviero
Paola Siviero@paolasiviero·
Qual opção é mais verdadeira? 1) A DEMANDA POR UM LIVRO É LATENTE: ela existe e quando uma editora/autor atende essa necessidade consegue vender bem 2) A DEMANDA POR UM LIVRO É CRIADA PÓS PUBLICAÇÃO através da divulgação. As pessoas só compram o que é esfregado na cara delas
Português
16
0
40
7.3K
Soneca
Soneca@sousoneca·
@softengini Orra! Dá pra vender por uma grana já
Português
1
0
1
15
Soneca
Soneca@sousoneca·
@paolasiviero A massa crítica pode vir de publicidade, seguidores em redes sociais, divulgação por ganhar prêmios, divulgação orgânica por influencers, leitores de seus livros anteriores. Mas, depois disso, é se o livro é recomendado para os amigos. E é muito difícil identificar o q gera isso.
Português
1
0
1
25
Soneca
Soneca@sousoneca·
@paolasiviero Eu acho que 1 é mais verdadeiro, mas a demanda latente é muito difícil (se não impossível) de se identificar a priori. Porque o que vende, na minha opinião, é livro que quem leu recomenda para outros lerem. Só precisa de uma massa crítica inicial de leitores /
Português
1
0
1
52