NILAY1556 (@nilay1556) 's Twitter Profile
NILAY1556

@nilay1556

ID: 1704827469256101888

calendar_today21-09-2023 11:58:51

36 Tweet

9 Takipรงi

51 Takip Edilen

NILAY1556 (@nilay1556) 's Twitter Profile Photo

Those small give up excuses like who care and noone see or notice I'm watching (myself) Fir se suru karenge, Kar ke dikhayenge

NILAY1556 (@nilay1556) 's Twitter Profile Photo

ffmpeg goat sota man! the model capabilities were secondary and to render these videos, many base great engineer things can't beat after with ai too

broski (@broskidotai) 's Twitter Profile Photo

just shipped rlm (recursive language model) cli it's based on recursive language models paper (arXiv:2512.24601), so the layman logic is instead of stuffing your entire context into one llm call and hoping it doesn't go into context rot, rlm writes code to actually process the

just shipped rlm (recursive language model) cli

it's based on recursive language models paper (arXiv:2512.24601), so the layman logic is instead of stuffing your entire context into one llm call and hoping it doesn't go into context rot, rlm writes code to actually process the
alphaXiv (@askalphaxiv) 's Twitter Profile Photo

"OpenClaw-RL: Train Any Agent Simply by Talking" OpenClaw-RLโ€™s big idea is that every time an AI agent gets a reply, error, test result, or tool output, itโ€™s already receiving free feedback. So instead of wasting those signals, this paper turns everyday use into live

"OpenClaw-RL: Train Any Agent Simply by Talking"

OpenClaw-RLโ€™s big idea is that every time an AI agent gets a reply, error, test result, or tool output, itโ€™s already receiving free feedback. 

So instead of wasting those signals, this paper turns everyday use into live
Kimi.ai (@kimi_moonshot) 's Twitter Profile Photo

Introducing ๐‘จ๐’•๐’•๐’†๐’๐’•๐’Š๐’๐’ ๐‘น๐’†๐’”๐’Š๐’…๐’–๐’‚๐’๐’”: Rethinking depth-wise aggregation. Residual connections have long relied on fixed, uniform accumulation. Inspired by the duality of time and depth, we introduce Attention Residuals, replacing standard depth-wise recurrence with

Introducing ๐‘จ๐’•๐’•๐’†๐’๐’•๐’Š๐’๐’ ๐‘น๐’†๐’”๐’Š๐’…๐’–๐’‚๐’๐’”: Rethinking depth-wise aggregation.

Residual connections have long relied on fixed, uniform accumulation. Inspired by the duality of time and depth, we introduce Attention Residuals, replacing standard depth-wise recurrence with
Het Bhalani (@het_bhalani) 's Twitter Profile Photo

HetGPT๐Ÿ‘ฝ - A multi model AI assistant! - Dual Memory System (STM+LTM) - Document RAG - Tool-augmented responses - Custom CS Model (Qwen3-8B fine-tuned with QLoRA) - Daily Rate-Limits GitHub: github.com/hetbhalani/Hetโ€ฆ

NILAY1556 (@nilay1556) 's Twitter Profile Photo

This is the first step i show towards other than just "AI-wrapper" and building something better than just calling api This is actual harness engineering