#dc_parallel_comp search results

Burke Holland

Oct 28

Multiple agents running in parallel in @code with Codex. You can adjust how long Codex thinks based on how hard to the problem is.

burkeholland's tweet image. Multiple agents running in parallel in @code with Codex. You can adjust how long Codex thinks based on how hard to the problem is.

central dogma specialist

@takimunk

Nov 5

run multiple simulations in parallel without worrying about self-exfiltration!

WEEK 18 EDUCATOR CONTEST - ROMA v2.0 - From Sequential to Parallel Execution You ever seen an AI stuck thinking line by line like it’s coding in 2005? ROMA said nah fam, intelligence doesn’t scale one thought at a time. Welcome to parallel reasoning - where multiple minds run…

thudongcnxnk's tweet image. WEEK 18 EDUCATOR CONTEST - ROMA v2.0 - From Sequential to Parallel Execution

You ever seen an AI stuck thinking line by line like it’s coding in 2005?

ROMA said nah fam, intelligence doesn’t scale one thought at a time.

Welcome to parallel reasoning - where multiple minds run…

Autor 🟪

@autor_becker

11 h

Why Parallel Thinking Makes AI Smarter, The ROMA Way @SentientAGI 🧵 Most AI system think in a straight way, they do tasks before the next task starts. That works but it is really slow & non-efficient.

autor_becker's tweet image. Why Parallel Thinking Makes AI Smarter, The ROMA Way @SentientAGI 🧵

Most AI system think in a straight way, they do tasks before the next task starts.
That works but it is really slow &amp; non-efficient.

Dr Milan Milanović

@milan_milanovic

Oct 13

𝗖𝗼𝗻𝗰𝘂𝗿𝗿𝗲𝗻𝘁 𝗶𝘀 𝗻𝗼𝘁 𝘁𝗵𝗲 𝘀𝗮𝗺𝗲 𝗮𝘀 𝗽𝗮𝗿𝗮𝗹𝗹𝗲𝗹 Most developers use these terms interchangeably. That's a mistake. 𝗖𝗼𝗻𝗰𝘂𝗿𝗿𝗲𝗻𝗰𝘆 is about structure. You design your program so that multiple tasks can progress simultaneously without waiting for…

milan_milanovic's tweet image. 𝗖𝗼𝗻𝗰𝘂𝗿𝗿𝗲𝗻𝘁 𝗶𝘀 𝗻𝗼𝘁 𝘁𝗵𝗲 𝘀𝗮𝗺𝗲 𝗮𝘀 𝗽𝗮𝗿𝗮𝗹𝗹𝗲𝗹

Most developers use these terms interchangeably. That's a mistake.

𝗖𝗼𝗻𝗰𝘂𝗿𝗿𝗲𝗻𝗰𝘆 is about structure. You design your program so that multiple tasks can progress simultaneously without waiting for…

dax

@thdxr

21 h

went through a bunch of code from PRs merged a while ago and cleaned them up and when i say "cleaned them up" i mean added more contexts

thdxr's tweet image. went through a bunch of code from PRs merged a while ago and cleaned them up

and when i say "cleaned them up" i mean added more contexts

Jiayi Pan

@jiayi_pirate

Apr 23

We explore a new dimension in scaling reasoning models in Adaptive Parallel Reasoning APR lets LMs learn to orchestrate both serial & parallel compute E2E via supervised training + RL — w/ better efficiency and scalability than long CoT on Countdown 🧵 arxiv.org/abs/2504.15466

jiayi_pirate's tweet image. We explore a new dimension in scaling reasoning models in Adaptive Parallel Reasoning

APR lets LMs learn to orchestrate both serial &amp; parallel compute E2E via supervised training + RL — w/ better efficiency and scalability than long CoT on Countdown

🧵 arxiv.org/abs/2504.15466

nasuy

@n_asuy

7 h

New parallelism for multiple agents: Claude Code, Codex, and Gemini

nasuy

@n_asuy

7 h

We can learn things from game UI for AI. loved UIs I played: - Detroit Become Human - NieR:Automata - Starfield ... To handle many tasks with a refined feel, we need a UX that differs from traditional B2B/B2C productivity apps. Expect that controlling a large number of AI…

n_asuy's tweet image. We can learn things from game UI for AI.

loved UIs I played:
- Detroit Become Human
- NieR:Automata
- Starfield
...

To handle many tasks with a refined feel, we need a UX that differs from traditional B2B/B2C productivity apps.

Expect that controlling a large number of AI…

Peter Kraft

@petereliaskraft

Oct 19, 2024

Scalability! But at what cost? This paper is an absolute classic because it explores the underappreciated tradeoffs of distributing systems. It asks about the COST of distributed systems--the Configuration that Outscales a Single Thread. The question is, how many cores does a…

petereliaskraft's tweet image. Scalability! But at what cost?

This paper is an absolute classic because it explores the underappreciated tradeoffs of distributing systems.

It asks about the COST of distributed systems--the Configuration that Outscales a Single Thread. The question is, how many cores does a…

Parallel Labs

@ParallelLabs_

Dec 8, 2021

🏆Parallel is now the 3rd largest crowdloan in total $DOT capitalization in the first round of Parachain auction crowdloans with 🤑10.69 million!

ParallelLabs_'s tweet image. 🏆Parallel is now the 3rd largest crowdloan in total $DOT capitalization in the first round of Parachain auction crowdloans with 🤑10.69 million!

maharshi

@mrsiipa

Jun 16, 2024

sum of two arrays in C but in parallel takes only 1.68 ms for 10,000 elements, nice.

Dan Murza

@dannothingnew

Nov 6

I fire up Claude code and can juggle multiple tasks with different agents running at the same time. Like, one agent catches mistakes in another agent's workflow and helps me fix them. Meanwhile, a third agent can review documentation or break down what someone else is working…

dannothingnew's tweet image. I fire up Claude code and can juggle multiple tasks with different agents running at the same time.

Like, one agent catches mistakes in another agent's workflow and helps me fix them.

Meanwhile, a third agent can review documentation or break down what someone else is working…

Josip

@l3d1c

Nov 5

12 Claude Code agents implementing features in parallel rn

Kieran Klaassen

@kieranklaassen

Jun 2

Claude Code can run multiple agents in parallel and synthesize them together at the end. In case you didn't know.

maharshi

@mrsiipa

Apr 27

understanding DDP is easy: these two functions are technically all you need to implement Distributed Data Parallel (DDP) model similar to PyTorch, from scratch.

mrsiipa's tweet image. understanding DDP is easy: these two functions are technically all you need to implement Distributed Data Parallel (DDP) model similar to PyTorch, from scratch.

Nathan Baschez

@nbashaw

Nov 3

Would love to see your AGENTS.md files Here is mine - designed for parallel agents running smoothly without git worktrees gist.github.com/nbashaw/946b18…

nbashaw's tweet image. Would love to see your AGENTS.md files

Here is mine - designed for parallel agents running smoothly without git worktrees gist.github.com/nbashaw/946b18…

Parallel Web Systems

@p0

Nov 6

Today, we’re launching the Parallel Search API, the most accurate web search for AI agents, built using our proprietary web index and retrieval infrastructure. Traditional search ranks URLs for humans to click. AI search needs something different: the right tokens in their…

Parallel

@ParallelTCG

Jul 22, 2023

𝗣𝗮𝗿𝗮𝗹𝗹𝗲𝗹 𝗖𝗼𝗹𝗼𝗻𝘆 Colony is a never ending game that is powered by AI where all in simulation items are onchain. You’re paired with a @Parallel Avatar who acts as boots on the ground and you work together and share onchain resources to navigate an ever expanding…