swarek🦍

6.9K posts

swarek🦍

swarek🦍

@Swarek_

vibecoder - https://t.co/x0RzDQ0d4F

Marseille, France เข้าร่วม Eylül 2014
190 กำลังติดตาม2.9K ผู้ติดตาม
swarek🦍
swarek🦍@Swarek_·
@nicdunz what can we wait for after this realtime 2 in voice ?
English
0
0
1
6
swarek🦍
swarek🦍@Swarek_·
@nicdunz I installed it and tried but never worked. The agent seemed to understand this /goal but just it was not reinjecting prompt
English
0
0
1
442
nic
nic@nicdunz·
guys, /goal is already in the codex app and has been since it was a thing. just put it in your prompt and send it and youll see. it doesnt show anything when you type it but it works. again: it does not show anything when you type it, but it works. just write it in your prompt and send it. idk why everyones struggling so much to do this.
English
18
3
186
16.5K
swarek🦍
swarek🦍@Swarek_·
@rileybrown I'll be on the next cohort for the testing if you want some prompts
English
2
0
6
4.2K
Riley Brown
Riley Brown@rileybrown·
I hardly ever say this... but my spidey senses are tingling... something is off about this. mark my words.
Alexander Whedon@alex_whedon

Introducing SubQ - a major breakthrough in LLM intelligence. It is the first model built on a fully sub-quadratic sparse-attention architecture (SSA), And the first frontier model with a 12 million token context window which is: - 52x faster than FlashAttention at 1MM tokens - Less than 5% the cost of Opus Transformer-based LLMs waste compute by processing every possible relationship between words (standard attention). Only a small fraction actually matter. @subquadratic finds and focuses only on the ones that do. That's nearly 1,000x less compute and a new way for LLMs to scale.

English
161
12
942
137.1K
Alexander Whedon
Alexander Whedon@alex_whedon·
Introducing SubQ - a major breakthrough in LLM intelligence. It is the first model built on a fully sub-quadratic sparse-attention architecture (SSA), And the first frontier model with a 12 million token context window which is: - 52x faster than FlashAttention at 1MM tokens - Less than 5% the cost of Opus Transformer-based LLMs waste compute by processing every possible relationship between words (standard attention). Only a small fraction actually matter. @subquadratic finds and focuses only on the ones that do. That's nearly 1,000x less compute and a new way for LLMs to scale.
English
1.5K
2.9K
23K
12.4M
swarek🦍
swarek🦍@Swarek_·
@alex_whedon That's amazing ! Just requested access, so hype to try it. You sell it for code, but is it interesting as a personal assistant ? Like natural speaking
English
0
0
0
43
Chubby♨️
Chubby♨️@kimmonismus·
Rumors so far: - Google Gemini Flash 3.2/3.5 (already being tested) - New Omni Model, maybe even updated Veo in competition to Seedance - "spark Robin" - new visual model?
English
51
47
1.3K
113.1K
TestingCatalog News 🗞
TestingCatalog News 🗞@testingcatalog·
OPENAI 👀: Codex app got updated to version 26.429.20946 with loads of minor tweaks and new hidden additions! What's hidden? (not available yet) - A new Remote Control feature and Connections section in settings - Codex "Avatars" got renamed into "Pets" - A new Keyboard category in settings for shortcut management - A new onboarding widget prompting to connect core integrations with email, calendar, and files What's new? - Updated onboarding flow - 20% faster computer & browser use - Upgraded slides and sheets capabilities - Annotation for browser, artifacts, and code - Cleaner design & performance improvements Additional changes? - It seems like Browser Use got disabled in EU - It seems like Computer Use got disabled in EU
TestingCatalog News 🗞 tweet media
Sam Altman@sama

big upgrade for codex today! try it for non-coding computer work.

English
26
38
752
80.2K
swarek🦍
swarek🦍@Swarek_·
@flowersslop @sama What does it misses for openclaw ? Real question, I never use openclaw but with the heartbeat in codex it's so cool
English
0
0
0
58
Flowers ☾
Flowers ☾@flowersslop·
@sama wen openclaw like superapp
English
2
0
27
1.4K
Sam Altman
Sam Altman@sama·
big upgrade for codex today! try it for non-coding computer work.
English
680
306
9.8K
786.6K
nic
nic@nicdunz·
IM SORRY WHAT?????? YOURE NOT SUPPOSED TO RINSE YOUR MOUTH AFTER YOU BRUSH YOUR TEETH???????
nic tweet media
English
30
2
123
21.2K
swarek🦍
swarek🦍@Swarek_·
@apizoizo Jsp tu te bases sur quoi pour les definitions toi ?
Français
2
0
33
1.7K
joz
joz@apizoizo·
@Swarek_ l’inceste c’est bien plus que ça mais ok merci larousse
Français
5
0
15
7.3K
joz
joz@apizoizo·
ça pose problème à personne l’INCESTE dans cette famille ?? wtf
Français
33
41
810
84.5K
swarek🦍
swarek🦍@Swarek_·
@Reshi_18 @KushinaGuccii Ma base morale : réduire la souffrance évitable et respecter le consentement, l’autonomie et l’intégrité des personnes. Le viol viole tout ça à la fois. Donc oui, il est mauvais sans avoir besoin d’un dieu pour le décréter
Français
0
0
0
39
DoubleL
DoubleL@Reshi_18·
@KushinaGuccii Les athées vous avez quel base morale objective pour affirmer que le viol est factuellement mauvais?
Français
911
5
85
1.8M
Hamza
Hamza@thegenioo·
@Swarek_ medium only bro 🥲
English
1
0
0
174
Hamza
Hamza@thegenioo·
GPT-5.5 is impressive, but it has destroyed the value of the $20 tier. Before the $100 plan, Plus was the most valuable subscription available. Now, with the new tier and GPT-5.5, the $20 plan works much like Claude’s $20 subscription. And it is unbearable.
Hamza tweet media
English
118
24
797
94K

ค้นพบ

@nicdunz @maxxrubin_ @OpenAIDevs @romainhuet @51jtm @andrealbriziom @nickaturley @rileybrown