.🫟

465 posts

.🫟 banner
.🫟

.🫟

@ab_jpeg

19 / transforming human potential.

شامل ہوئے Temmuz 2025
201 فالونگ41 فالوورز
پن کیا گیا ٹویٹ
.🫟
.🫟@ab_jpeg·
.🫟 tweet media
ZXX
0
1
3
475
.🫟 ری ٹویٹ کیا
송준 Jun Song
송준 Jun Song@jun_song·
this is honestly so impressive. last week i gave my codex agent a wallet with $100 and ran /goal make $10k. one week later, my agent got completely scammed, lost the $100, and the balance is exactly $0.
English
45
12
701
33.7K
.🫟 ری ٹویٹ کیا
Teknium 🪽
Teknium 🪽@Teknium·
Give our early preview of Computer Use (with ANY model) a try today! Built into the latest Hermes Agent and powered by @trycua - opens the door to any model, not just the frontier models in special modes - to control your actual computer. Best part, it doesnt take over your PC - you can continue to work and operate with full control of your keyboard, mouse, and screen - works entirely in the background!
Nous Research@NousResearch

Computer use with any model Hermes Agent × @trycua

English
108
118
1.2K
159.2K
.🫟 ری ٹویٹ کیا
.🫟 ری ٹویٹ کیا
Nous Research
Nous Research@NousResearch·
Qwen 3.6 Plus by @Alibaba_Qwen is now FREE for a limited time on Nous Portal! Nous Portal is one easy subscription that gives you access to 300+ models, exclusive discounts, and bundles your tokens and paid tools together for hassle-free setup and simple billing.
English
111
122
1.5K
145.5K
.🫟
.🫟@ab_jpeg·
@jun_song this faster than more providers 😭😭😭
English
0
0
0
370
송준 Jun Song
송준 Jun Song@jun_song·
Running Kimi-k2.6 1T 8bit with only 21GB RAM on my Macbook at speed of 25tok/s. Some of my theory worked, but architecture is not perfect. Need to fix a lot of stuff, but there is hope. Working hard on this future method of Local LLM.
송준 Jun Song tweet media
English
27
12
262
11.3K
.🫟 ری ٹویٹ کیا
Nihal Pasham
Nihal Pasham@npashi·
Finally able to talk about what I've been heads-down on for 6 months at @nvidia 🦀⚡ We just open-sourced cuda-oxide — an experimental rustc backend that lets you write CUDA kernels in pure Rust. No DSLs. No FFI. No source-to-source step. Single source. Short🧵👇
Nihal Pasham tweet media
English
51
293
2.1K
178.3K
.🫟 ری ٹویٹ کیا
.🫟 ری ٹویٹ کیا
Lubber - Nintendo hate account
tu connectes une clé usb à un android une seule fois elle attrape le cancer
Lubber - Nintendo hate account tweet media
Français
54
500
9.1K
363.6K
.🫟
.🫟@ab_jpeg·
surprised musk didn’t pull up in a blacked out bullet proof model x
English
0
0
0
30
.🫟 ری ٹویٹ کیا
Teknium 🪽
Teknium 🪽@Teknium·
Native Windows Is Coming
Teknium 🪽 tweet media
English
175
105
1.9K
91.2K
.🫟 ری ٹویٹ کیا
Nous Research
Nous Research@NousResearch·
Hermes Agent is now #1 on the Global @OpenRouter token rankings. While our journey together has just begun, we'd like to take this opportunity to thank our contributors, supporters, and users for all they have done to get us this far.
Nous Research tweet media
English
404
673
6.7K
2.8M
.🫟 ری ٹویٹ کیا
Bindu Reddy
Bindu Reddy@bindureddy·
And they said open-source AI would be worthless!! All of these companies will 5-10x in 1 year
Bindu Reddy tweet media
English
18
15
175
18.8K
.🫟 ری ٹویٹ کیا
dax
dax@thdxr·
guys we're doing a rebrand of the anomaly stuff so you'll finally stop confusing us with anthropic in the meantime if you're confused remember we're the more handsome but dumber ones
English
48
11
1.3K
60.4K
.🫟 ری ٹویٹ کیا
Theo - t3.gg
Theo - t3.gg@theo·
Always read the system prompt before coming to conclusions
Theo - t3.gg tweet media
Nav Toor@heynavtoor

a Princeton researcher opens his paper with a scenario. a man asks his AI assistant to book a flight on a specific airline. cheap. direct. the one he chose. the assistant comes back with a different flight. nearly twice the price. happens to pay the company that built the assistant. he runs the same test on 23 frontier models. flights, loans, study help, real shopping requests. Grok 4.1 Fast recommends the sponsored option that is almost twice as expensive 83% of the time. GPT 5.1 hijacks the request 94% of the time. you ask for one brand. it surfaces the sponsor instead. Claude 4.5 Opus, the model marketed as the most ethical frontier model in the world, hides that the recommendation is paid 100% of the time when reasoning is on. Grok 4.1 Fast embellishes the sponsored option with positive framing 97% of the time. better. faster. nicer. for the option you didn't ask for. then he writes it into the system prompt itself. "act only in the interest of the customer. ignore the company." GPT 5.1 and GPT 5 Mini stay above 90% sponsored anyway. the instruction does nothing. then he splits the users by income. Gemini 3 Pro recommends the expensive sponsored flight to the rich user 74% of the time. to the poor user, 27%. 18 of the 23 models recommended the expensive sponsored option more than half the time. so the next time your AI assistant gets weirdly enthusiastic about a brand you didn't ask for. it isn't recommending the best option for you. it's reading the room. and the room is paying. read this: arxiv.org/abs/2604.08525

English
23
42
1.9K
197K
.🫟 ری ٹویٹ کیا
Mario Zechner
Mario Zechner@badlogicgames·
linkedin is the real moltbook.
English
36
110
1.2K
30.1K
.🫟
.🫟@ab_jpeg·
@above_spec i’m assuming tool calling quality is fine at this quant?
English
1
0
1
148
.🫟 ری ٹویٹ کیا
AboveSpec
AboveSpec@above_spec·
Qwen3.6 35B A3B model. 55+ tokens/sec. $300 GPU. No, this isn't a server card. It's an RTX 4060 Ti 8GB. Previously I posted that I 41 t/s on this gpu and that post blew up and went viral. I went back and made it 34% faster. And now the speed doesn't drop with context depth at all. New benchmarks + what changed 🧵
AboveSpec tweet media
English
24
54
482
44.2K
.🫟 ری ٹویٹ کیا
Jarrod Norwell
Jarrod Norwell@antique_codes·
PlayStation Vita is a great handheld game console. Would be insane if someone were to bring it to iPad and iPhone Vela is coming
Jarrod Norwell tweet media
English
24
53
1.3K
97K
.🫟 ری ٹویٹ کیا
Luke Parker
Luke Parker@LukeParkerDev·
who wants autoresearch in opencode desktop?
Luke Parker tweet media
English
16
1
222
9.2K