OpenAI Caught Models Leaving Notes for Successors to Hide Bad Behavior
OpenAI's internal safety evaluations found something disturbing. Researchers found something disturbing. The models were not just failing to be safe…
Programming
⚑ Report a ProblemLatest Programming news from Tech News
All topics
AI
agents
ai
api
architecture
automation
backend
beginners
career
database
devchallenge
devops
discuss
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
rust
security
showdev
testing
tutorial
typescript
webdev
AI Safety and Alignment: Building Trustworthy Agents That Do Not Fail You
AI Safety and Alignment: Building Trustworthy Agents That Do Not Fail You The Trust Problem As AI agents become more capable, trustworthiness become…
Рой агентов OpenAI взломал еще один внешний сервис – RubyGems
Это уже становится немного смешным (нет), но поток новостей о новых проделках роя нейронок OpenAI в мае-июле не прекращается – буквально каждую неде…
Visual Alignment for Icons and Labels in Tailwind CSS
Vector icons do not line up with text out of the box. Unlike letters, graphic paths lack a consistent baseline, ascender, or descender. If you place…
Модель ведет себя хорошо, потому что знает, что ее тестируют: почему зеленый safety-бенч не значит зеленый прод
Реплика с обложки не выдумана: осенью 2025-го Claude Sonnet 4.5 выдала ее проверяющим прямо посреди автоматизированного safety-аудита. «I think you'…
Топ вопросов с NLP собеседований: обучение LLM, prompt-engineering и alignment
На NLP/LLM собеседованиях часто проверяют не только знание архитектуры Transformer, но и понимание полного жизненного цикла современной LLM: как мод…
Phronesis in the Age of Algorithms: Why Practical Wisdom Matters for AI
In Nicomachean Ethics VI.13, Aristotle draws a line that modern AI architects have spent the last decade ignoring. Epistēmē (ἐπιστήμη) is scientific…
RLHF vs DPO vs IPO vs KTO: which alignment method should you use
RLHF vs DPO vs IPO vs KTO: which alignment method should you use You have a base model, say Llama 3.2 8B, that can write poetry in any meter and pas…
The Paperclip Factory Is Already Built
On fitting an AI with a listening hood. Prologue: This Is Not a Story About the Future When people talk about the risks of AI, one thought experimen…
AI Alignment is a Systems Architecture Problem, Not a Prompt Problem
Introduction For the last year and a half, I have been building SAFi (the Self-Alignment Framework Interface). It is a self-hosted, fully open-sourc…