Skip to content

/

ZeroHour

ZeroHour aggregates public sources — security and AI press, vendor advisories, NVD, CISA KEV, FIRST EPSS, leak-site trackers and Have I Been Pwned — and classifies them with AI. Summaries can be wrong: read the original. All times are UTC.

News CVEs Incidents Tags Daily brief Traffic Sources RSS & API Kiosk Health Sitemap

Home
News feed
Exploited now

Security

CVEs
Ransomware & breaches
Threat actors & entities
IOCs

AI

AI & models

Explore

Tags
Daily brief
Analytics
Traffic & readers
Ask the feed
Sources

You

Watchlist
Saved
RSS, API & alerts

09:57 UTC· just now

#rlhf — news, CVEs and analysis · ZeroHour

today 56 visits · 73 views · 11 reads·all time 17K views

Tag

#rlhf

2 stories this week · 10 this month · 12 in 6 months · mostly AI

stories per day · 30 days

Related#agents 2 #alignment 2 #dpo 2 #jev 2 #likelihood-displacement 2 #openai 2 #post-training 2 #preference-alignment 2 #preference-optimization 2 #reinforcement-learning 2 #zeroth-order-optimization 2 #advertising 1 #ai-safety 1 #anthropic 1 #board-appointment 1 #calibrated-decisions 1 #calibration 1 #chatgpt 1

12 stories, newest first · one card per story

Latent Space·2d ago

Jev: System One models for Prod, not God — with Diogo Almeida, CEO, TypeSafe AI

#jev #typesafe #rlcd

4 sources 15 min

Hugging Face daily papers·3d ago

Rufus-Air: An Open LLM Post-Training Recipe

#post-training #sft #reinforcement-learning

TechCrunch · AI·8d ago

A new kind of AI model from a ChatGPT inventor is thrilling developers

#calibrated-decisions #jev #llm-alternative

4 min

arXiv cs.AI / cs.LG / cs.CL·10d ago

A Zeroth-Order Paradigm for LLM Preference Alignment

#compo #likelihood-displacement #llm

AI research

Hugging Face daily papers·11d ago

Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

#critic-learning #ppo #preference-optimization

Hugging Face daily papers·11d ago

A Zeroth-Order Paradigm for LLM Preference Alignment

#likelihood-displacement #post-training #preference-alignment

1

404 Media·12d ago

Inside ‘Project Lily’: The Humans Reading Your ChatGPT Chats

#anthropic #chatgpt #human-review

11 min

TechCrunch · AI·17d ago

OpenAI adds a prominent AI doomer to its board of directors

#ai-safety #alignment #board-appointment

3 min

Hugging Face daily papers·27d ago

PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization

#alignment #dpo #noisy-labels

Hugging Face daily papers·27d ago

AgenticGen: Reward-Guided Agentic Video Generation for Advertising

#advertising #agents #dpo

Interconnects·Aug 12, 2026

I wrote an AI textbook — how long until AI can do it better?

#llm #long-form #model-capabilities

11 min

Interconnects·Aug 10, 2026

5 useful things you'll learn in my new post-training textbook (shipping now!)

#grpo #llm #post-training

7 min1