scalalang2's profile picture. 멍청한 프로그래머 - 가끔 글도 씁니다 / All opinions are my own

scalalang

@scalalang2

멍청한 프로그래머 - 가끔 글도 씁니다 / All opinions are my own

scalalang reposted

🚨 This might be the biggest leap in AI agents since ReAct. Researchers just dropped DeepAgent a reasoning model that can think, discover tools, and act completely on its own. No pre-scripted workflows. No fixed tool lists. Just pure autonomous reasoning. It introduces…

rryssf_'s tweet image. 🚨 This might be the biggest leap in AI agents since ReAct.

Researchers just dropped DeepAgent a reasoning model that can think, discover tools, and act completely on its own.

No pre-scripted workflows. No fixed tool lists. Just pure autonomous reasoning.

It introduces…

Perplexity AI 브라우저가 새롭게 출시해서 써봤는데, Captcha의 벽을 넘지 못하고 있음

scalalang2's tweet image. Perplexity AI 브라우저가 새롭게 출시해서 써봤는데, Captcha의 벽을 넘지 못하고 있음

어디서 많이 보던

The biggest application of MCP servers: building them

Hesamation's tweet image. The biggest application of MCP servers: 
building them


하 이녀석.. 힘들었다

scalalang2's tweet image. 하 이녀석.. 힘들었다

scalalang reposted

Having seen a few different blog posts like this, I am convinced that with a small team and limited funding it's possible to build a half decent, actually useful, text search engine as a working consumer-facing product. However, I don't know if the same can be said for searching…

this is one of the most remarkable technical blog posts I’ve ever read

Talor_A's tweet image. this is one of the most remarkable technical blog posts I’ve ever read


scalalang reposted

🚨 HUGE NEWS: OpenAI Claims to have found the cause of hallucinations This could be the next big unhobbling. That is not hype.

daniel_mac8's tweet image. 🚨 HUGE NEWS: OpenAI Claims to have found the cause of hallucinations

This could be the next big unhobbling.

That is not hype.

scalalang reposted

Create an insane AI anime with Nano Banana and Seedance 1.0 It's easy and takes less than 2 hours Here's what to do 👇


scalalang reposted

A team at DeepMind wrote this solid piece on how you must think about GPUs. Essential for AI engineers and researchers.

rohanpaul_ai's tweet image. A team at DeepMind wrote this solid piece on how you must think about GPUs. Essential for AI engineers and researchers.

scalalang reposted

Our paper on autonomous scientific research is accepted to Findings of #EMNLP2025! 🎉 We introduce Agent Laboratory, a framework that accelerates scientific discovery by teaming human researchers with LLM agents.

SRSchmidgall's tweet image. Our paper on autonomous scientific research is accepted to Findings of #EMNLP2025! 🎉

We introduce Agent Laboratory, a framework that accelerates scientific discovery by teaming human researchers with LLM agents.

scalalang reposted

Hollow Knight: Silksong. Two weeks. #NintendoSwitch2 #NintendoSwitch

NintendoEurope's tweet image. Hollow Knight: Silksong.

Two weeks.

#NintendoSwitch2 #NintendoSwitch

scalalang reposted

Shout out to one of our very own programmers, @joespacio, whose entry Draftula placed FIRST in the Enjoyment category for GMTK Game Jam 2025!! 🥇✨ Try out this Tetris roguelike for yourself here!! ➡️ joespacio.itch.io/draftula

MegaCrit's tweet image. Shout out to one of our very own programmers, @joespacio, whose entry Draftula placed FIRST in the Enjoyment category for GMTK Game Jam 2025!! 🥇✨

Try out this Tetris roguelike for yourself here!! ➡️ joespacio.itch.io/draftula

For the GMTK jam this year I made a little Tetris roguelike called Draftula. Build up the castle by strategically placing rooms and see how high you can make it before the hero comes to ruin your fun! you can find the link in the replies #GMTK2025 #GMTK #gamedev



이놈들아 드디어 나오냐?

The countdown is on! Join us in 48 hours for a special announcement about Hollow Knight: Silksong! Premiering here: youtu.be/6XGeJwsUP9c

TeamCherryGames's tweet image. The countdown is on!

Join us in 48 hours for a special announcement about Hollow Knight: Silksong!

Premiering here: youtu.be/6XGeJwsUP9c


scalalang reposted

𝑳𝑳𝑴𝒔 can really 𝑺𝒆𝒍𝒇-𝑬𝒗𝒐𝒍𝒗𝒆, 𝒘𝒊𝒕𝒉𝒐𝒖𝒕 𝑯𝒖𝒎𝒂𝒏 𝑫𝒂𝒕𝒂! -- One LLM, two roles: Challenger creates tasks, Solver answers them. -- No data, no labels, just a base model that learns and improves itself! We name it 𝑹-𝒛𝒆𝒓𝒐: arxiv.org/abs/2508.05004

wyu_nd's tweet image. 𝑳𝑳𝑴𝒔 can really 𝑺𝒆𝒍𝒇-𝑬𝒗𝒐𝒍𝒗𝒆, 𝒘𝒊𝒕𝒉𝒐𝒖𝒕 𝑯𝒖𝒎𝒂𝒏 𝑫𝒂𝒕𝒂!

-- One LLM, two roles: Challenger creates tasks, Solver answers them.
-- No data, no labels, just a base model that learns and improves itself!

We name it 𝑹-𝒛𝒆𝒓𝒐: arxiv.org/abs/2508.05004

Loading...

Something went wrong.


Something went wrong.