#nothinking
LightNews LightNews
sberryradio.bsky.social
Positive art/fic train with things I already have on the phone and really nothinking tags!

Thanks to my n°1 fan @crashbandicoot96.bsky.social for the tag!

@paolaca18229.bsky.social
@hazelnart.bsky.social
@spiderpotion.bsky.social
@itsmarsmol.bsky.social
@jowah.bsky.social
February 7, 2026 at 3:58 PM
chuckandgeorge.bsky.social
#drinkbleach #trumpsucks #magasucks #fucktrump #theylive #consume #obey #nothinking
March 4, 2025 at 3:13 AM
newdlebobs.bsky.social
'Tivli Moonrest - Too thicc to think.' now available!!

#newdlebob #newdlebobs #newdle #artmoot #artmoots #moots #meme #memes #shirts #memeshirts #gift #gifts #memegift #merch #toothicctothink #toothicc #nothinking #nothoughts
December 8, 2025 at 5:30 PM
newdlebobs.bsky.social
'Cobbler Firgrove - Too thicc to think.' now available!!

#newdlebob #newdlebobs #newdle #artmoot #artmoots #meme #memes #toothicctothink #toothicc #nothinking #nothoughts
September 11, 2025 at 7:48 PM
rachel5742.eurosky.social
Yes...and I'm still Nothinking of him.
June 21, 2025 at 7:21 PM
hm2b.bsky.social
You wanted trudeau gone...NOTHINKING PERSON SAYS YOU HAVE REAL POLICY...SUCH NONSENSE
May 9, 2025 at 7:28 PM
dalekaramazov.bsky.social
Overthinking acabou, hoje é Nothinking
September 8, 2024 at 1:50 PM
galapula.bsky.social
Just going to think about the Lions game today and nothing about the impending doomshit on Monday. #onepride #nothinking
January 18, 2025 at 3:28 PM
rachel5742.eurosky.social
I had to survive and throughout the ordeal I was Nothinking of you.
@kacidama.bsky.social
@evlenz.bsky.social
@jfritte.bsky.social
@ailsalaing.bsky.social
@valeriea.bsky.social
@lomquiche.bsky.social
@dfarb.bsky.social
@natsommers.bsky.social
@rogerday.bsky.social
@stephenold.bsky.social
an older woman is standing in front of a window wearing a green jacket and a floral shirt .
ALT: an older woman is standing in front of a window wearing a green jacket and a floral shirt .
media.tenor.com
June 12, 2025 at 10:48 AM
createdbyrcw.bsky.social
ONLY FOUR SPOTS LEFT in our #storytelling & #improv silly-lympics!

JOIN the world of freewheeling #stories & spontaneous #creativity in OUT OF OUR MINDS (& ONTO THE PAGE)

Starts Sat, Jan 10 @ Sweet Action Theatre! LEARN MORE AT: createdbyrcw.com

#NoThinking #NoPreparation #writing #play #games
January 2, 2026 at 2:57 AM
createdbyrcw.bsky.social
WHAT IF:
#Writing was #fun?
#Storytelling felt #safe?
#Playing with ideas felt #magical?

There’s no “what if” about it in OUT OF OUR MINDS (& ONTO THE PAGE) where we #play to #create!

25% off with discount code MAYHEM.
Learn more at: createdbyrcw.com

#NoPrep #NoThinking #creativity
April 26, 2026 at 2:43 PM
createdbyrcw.bsky.social
THE REVIEWS ARE IN!

OUT OF OUR MINDS (& ONTO THE PAGE) GETS WRITERS WRITING!

Next 5-week session of #improvised #storytelling starts in May @ Toronto’s SoCap Comedy Theatre

To register or learn more: createdbyrcw.com

#creativity #selfexpression #games #fun #improv #NoThinking
April 4, 2026 at 3:34 PM
paper.bsky.social
[19/30] 110 Likes, 26 Comments, 2 Posts
2504.09858, cs․AI | cs․CL, 14 Apr 2025

🆕Reasoning Models Can Be Effective Without Thinking

Wenjie Ma, Jingxuan He, Charlie Snell, Tyler Griggs, Sewon Min, Matei Zaharia
Recent LLMs have significantly improved reasoning capabilities, primarily by including an explicit, lengthy Thinking process as part of generation. In this paper, we question whether this explicit thinking is necessary. Using the state-of-the-art DeepSeek-R1-Distill-Qwen, we find that bypassing the thinking process via simple prompting, denoted as NoThinking, can be surprisingly effective. When controlling for the number of tokens, NoThinking outperforms Thinking across a diverse set of seven challenging reasoning datasets--including mathematical problem solving, formal theorem proving, and coding--especially in low-budget settings, e.g., 51.3 vs. 28.9 on ACM 23 with 700 tokens. Notably, the performance of NoThinking becomes more competitive with pass@k as k increases. Building on this observation, we demonstrate that a parallel scaling approach that uses NoThinking to generate N outputs independently and aggregates them is highly effective. For aggregation, we use task-specific verifiers when available, or we apply simple best-of-N strategies such as confidence-based selection. Our method outperforms a range of baselines with similar latency using Thinking, and is comparable to Thinking with significantly longer latency (up to 9x). Together, our research encourages a reconsideration of the necessity of lengthy thinking processes, while also establishing a competitive reference for achieving strong reasoning performance in low-budget settings or at low latency using parallel scaling.
April 26, 2025 at 12:06 AM
createdbyrcw.bsky.social
COME JOIN THE FUN as we explore #storytelling through #improv #games & #writing sprints in OUT OF OUR MINDS & ONTO THE PAGE

EARLY-BIRD PRICING AFTER ENDS JULY 4

createdbyrcw.com/2025/06/07/o...

#selfexpression #play #silliness #nopressure #nothinking #justfun
July 3, 2025 at 1:54 PM
alphaxiv.org
Reasoning Models Can Be Effective Without Thinking

This paper challenges the need for explicit chain-of-thought reasoning in large language models by proposing a simple prompting method—NoThinking—that skips the verbose thinking process yet achieves strong performance.
April 19, 2025 at 8:16 PM
createdbyrcw.bsky.social
WHAT IF:
#Writing was #fun?
#Storytelling felt #safe?
#Playing with ideas felt #magical?

There’s no “what if” about it in OUT OF OUR MINDS (& ONTO THE PAGE) where we #play to #create!

Learn more at: createdbyrcw.com

#NoPrep #NoThinking #creativity #TorontoEvents
Testimonials around me in a Hawai’ian shirt (Photo by Marlon Kunreich)
March 13, 2026 at 4:54 PM
createdbyrcw.bsky.social
Next OUT OF OUR MINDS (& ONTO THE PAGE) coming in May!

Make #writing & #storytelling spontaneous & freewheeling with #improv #games & sprints!

Visit createdbyrcw.com for details

#NoThinking #NoPrep #NoHomework #play
@ce-gbpolytech.bsky.social @gbpolytech.bsky.social
February 19, 2026 at 8:06 PM
pinoakkey.bsky.social
バトラー『分かれ道』第6章読了。本章でバトラーは、アーレントにおける「共生」と「思考」の関係について考察している。『エルサレムのアイヒマン』を通じて、バトラーは、アーレントがアイヒマンを非難するのは、彼らが犯した罪は「考えることの失敗」であったからだと述べる。本来、誰と共に生きるかを選択することはできないが、アイヒマンらは共生の相手を選択可能である、言い換えれば、特定の他者を排除可能であると考えてしまった。この「共生の非選択性」を「考えないこと[nothinking]の帰結がジェノサイド的」なのだ。
February 24, 2025 at 1:46 AM
createdbyrcw.bsky.social
ONLY TWO DAYS LEFT FOR EARLY-BIRD PRICING! SAVE $56.50!

REGISTER NOW TO BECOME A FREEWHEELING, SPONTANEOUS #STORYTELLER!

#IMPROV GAMES + #WRITING SPRINTS = OUT OF OUR MINDS (& ONTO THE PAGE)

createdbyrcw.com/2025/06/07/o...

#storytelling #play #silliness #selfexpression #nothinking #nopressure
July 2, 2025 at 6:19 PM
createdbyrcw.bsky.social
Let’s #play #games & turn you into a freewheeling #storyteller & #writer!

DON’T MISS your chance to join the chaotic #fun of OUT OF OUR MINDS (& ONTO THE PAGE) at Toronto’s Sweet Action Theatre.

TO REGISTER OR FOR INFO: createdbyrcw.com/2025/06/07/o...

#storytelling #writing #improv #nothinking
July 5, 2025 at 4:32 PM
hauntedtypewriter.bsky.social
The party told you to reject the evidence of your eyes and ears. It was their final, most essential command. #BigBrotherIsWatching #NineteenEightyFour #MediaControl #MindControl #KnowYourEnemy #YouAreFreeToChooseWhatWeTellYouToChoose #Orwellian #NoThinking #Propaganda #DoNotDeviate #FreeSpeech
two news programs on fox news - 'left has a history of fawning over killers' and the next segment the news host is fawning over a killer
December 11, 2024 at 12:34 AM
paper.bsky.social
[30/30] 243 Likes, 3 Comments, 2 Posts
2505.13417, cs․CL | cs․AI | cs․LG, 19 May 2025

🆕AdaptThink: Reasoning Models Can Learn When to Think

Jiajie Zhang, Nianyi Lin, Lei Hou, Ling Feng, Juanzi Li
Recently, large reasoning models have achieved impressive performance on various tasks by employing human-like deep thinking. However, the lengthy thinking process substantially increases inference overhead, making efficiency a critical bottleneck. In this work, we first demonstrate that NoThinking, which prompts the reasoning model to skip thinking and directly generate the final solution, is a better choice for relatively simple tasks in terms of both performance and efficiency. Motivated by this, we propose AdaptThink, a novel RL algorithm to teach reasoning models to choose the optimal thinking mode adaptively based on problem difficulty. Specifically, AdaptThink features two core components: (1) a constrained optimization objective that encourages the model to choose NoThinking while maintaining the overall performance; (2) an importance sampling strategy that balances Thinking and NoThinking samples during on-policy training, thereby enabling cold start and allowing the model to explore and exploit both thinking modes throughout the training process. Our experiments indicate that AdaptThink significantly reduces the inference costs while further enhancing performance. Notably, on three math datasets, AdaptThink reduces the average response length of DeepSeek-R1-Distill-Qwen-1.5B by 53% and improves its accuracy by 2.4%, highlighting the promise of adaptive thinking-mode selection for optimizing the balance between reasoning quality and efficiency. Our codes and models are available at https://github.com/THU-KEG/AdaptThink.
June 16, 2025 at 12:06 AM
arxiv-cs-cl.bsky.social
Bo Cheng, Qiaolin Lu, Yi Chang, Yuan Wu
Thinking vs. NoThinking: Towards Interpreting Reasoning Mechanisms of Large Language Models via Sparse Autoencoders
https://arxiv.org/abs/2608.08168
August 12, 2026 at 2:04 AM
cscl-bot.bsky.social
Bo Cheng, Qiaolin Lu, Yi Chang, Yuan Wu: Thinking vs. NoThinking: Towards Interpreting Reasoning Mechanisms of Large Language Models via Sparse Autoencoders https://arxiv.org/abs/2608.08168 https://arxiv.org/pdf/2608.08168 https://arxiv.org/html/2608.08168
August 11, 2026 at 6:39 AM
paper.bsky.social
2505.13417
近年、大規模な推論モデルは、人間のような深い思考を採用することで、様々なタスクで素晴らしいパフォーマンスを達成している。しかし、長時間の思考プロセスは推論のオーバーヘッドを大幅に増加させるため、効率が重要なボトルネックとなる。この研究では、まず、推論モデルに思考をスキップさせ、最終的な...
近年、大規模な推論モデルは、人間のような深い思考を採用することで、様々なタスクで素晴らしいパフォーマンスを達成している。 しかし、長時間の思考プロセスは推論のオーバーヘッドを大幅に増加させるため、効率が重要なボトルネックとなる。 この研究では、まず、推論モデルに思考をスキップさせ、最終的な解を直接生成するよう促すNoThinkingが、パフォーマンスと効率の両面において、比較的単純なタスクに適した選択であることを示す。 このことに動機づけられ、我々は、問題の難易度に基づいて適応的に最適な思考モードを選択するように推論モデルを教える新しいRLアルゴリズムであるAdaptThinkを提案する。 具体的には、AdaptThinkは2つのコアコンポーネントを備えている：(1)全体的なパフォーマンスを維持しながら、モデルがNoThinkingを選択するよう促す制約付き最適化目的、(2)オンポリシー訓練中にThinkingとNoThinkingのサンプルをバランスさせる重要度サンプリング戦略、それによりコールドスタートを可能にし、訓練プロセスを通してモデルが両方の思考モードを探索し、利用することを可能にする。 我々の実験によれば、AdaptThinkは推論コストを大幅に削減すると同時に、パフォーマンスをさらに向上させる。 注目すべきは、3つの数学データセットにおいて、AdaptThinkはDeepSeek-R1-Distill-Qwen-1.5Bの平均応答長を53%短縮し、精度を2.4%向上させたことで、推論の質と効率のバランスを最適化する適応的思考モード選択の有望性が浮き彫りになった。 当社のコードとモデルはhttps://github.com/THU-KEG/AdaptThink。
June 16, 2025 at 12:07 AM