AI Reasoning

Feeds to Scour
SubscribedAll
Scoured 275 posts in 8.6 ms

ReasoningFlow: Discourse Structures for Understanding LLM Reasoning Traces

 🖥️Inference Compute  Content type: Academic
arxiv.org·

Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models

 🧠LLMs
lesswrong.com·
Less-relevant results

No Token Left Behind: Demystifying Token-in-Token-Out in Miles

 🖥️Inference Compute  Content type: Blog
lmsys.org··Hacker News

Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AI

 🔓Open-source Models  Content type: Blog
huggingface.co·

Claude Fable 5 🚀, Gemini 3.5 Live Translate 📱, scaling test time compute 📈

 🕵️AI Agents
tldr.tech·

Transitioning from Azure Language Features to Foundry Models

 🎭Multimodal AI

😸 WATCH: Sleeping on Microsoft AI? Whoops.

 🕵️AI Agents
theneurondaily.com·

Reasoning RL in 2026: GRPO, DPO, RLVR, Agentic PO & Beyond

 🎮RL
turingpost.com·

Tokenminning: Because Tokenmaxxing Is a Bad Idea

 🧠LLMs

If LLMs are all persona, whose persona are they?

 🖥️Inference Compute

BacteReason: A Reasoning Model for Antimicrobial Resistance Prediction

 🖥️Inference Compute  Content type: Academic
biorxiv.org·

Microsoft open sources AI evaluation framework for enterprise agents

 🕵️AI Agents  Content type: News
infoworld.com·

Researchers say they trained a foundation model from scratch for about $1,500

 🖥️Inference Compute
venturebeat.com··Hacker News

KiloBench - Because Your Benchmark Score Doesn't Pay the Bill

 🕵️AI Agents  Content type: News  Content type: Blog
blog.kilo.ai·

OpenAI launches GPT-Rosalind and biodefense action plan for biological security

 🖥️Inference Compute
4sysops.com·

Microsoft just shared the frontier data engineering secrets

 🕵️AI Agents
mail.bycloud.ai·

NVIDIA Nemotron 3 Ultra Powers Faster, More Efficient Reasoning for Long-Running Agents

 🕵️AI Agents  Content type: Blog

Calibration Drift Under Reasoning: How Chain-of-Thought Budgets Induce Overconfidence in Large Language Models

 🧠LLMs  Content type: Academic
arxiv.org·

Why Claude Produces High-Quality Output: A Developer’s Guide to Token Efficiency and Hallucination…

 🧠LLMs  Content type: Blog
medium.com·

The AI Convergence Problem

 🖥️Inference Compute

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help