Hackernews posts about Anthropic and Alignment

RSS feed for Anthropic and Alignment

01
newAnthropic and Alignment (Ben Thompson)stratechery.com
▲ 22toomanybits 250d 💬 17
02
newAnthropic and Alignmentstratechery.com
▲ 3stochastician 250d discuss
03
newYou're not a founder, you're a gig worker
▲ 30tsunamifury 478d 💬 11
04
newImproving our alignment and security effortswww.anthropic.com
▲ 27reasonableklout 67d 💬 18
05
newAnthropic Urges Global Pause in AI Development, Flags 'Self-Improvement' Risk
▲ 9stefap2 156d 💬 8
06
newImproving our alignment and security practiceswww.anthropic.com
▲ 6surprisetalk 68d 💬 1
07
newImproving our alignment and security effortswww.anthropic.com
▲ 5jbegley 67d 💬 4
08
newShow HN: BreakMyAgent – Open-source red-teaming sandbox for LLM system prompts
▲ 2breakmyagent 254d discuss
09
newShow HN: Trust Protocols for Anthropic/OpenAI/Geminiwww.mnemom.ai
▲ 40alexgarden 262d 💬 33
10
newShow HN: ChatGPT's Infinite Memory Lies – Anthropic Paper Explainer
▲ 3marima2 569d 💬 2
11
newShow HN: How to analyze your LLM output – A behavioural health monitor for LLMssplabs.io
▲ 10k-thimmaraju 172d 💬 7
12
newHow does misalignment scale with model intelligence and task complexity?alignment.anthropic.com
▲ 242salkahfi 278d 💬 78
13
newShow HN: Pantheon-CLI – Open-Source Python Claude Code and Smart Notebookgithub.com
▲ 6steorra 438d 💬 7
14
newSafety Ideas, and a Testable Path
▲ 2GrizzlyMedicine 145d 💬 1
15
newTraining and Evaluating LLMs as General-Purpose Activation Explainersalignment.anthropic.com
▲ 1not4uffin 323d discuss
16
newShow HN: Cupcake – Better performance and security for coding agents (via OPA)github.com
▲ 12ramoz 332d 💬 1
17
newShow HN: I built a web tool to see and edit what an AI thinks before it answerslucid.earthpilot.ai
▲ 34ada1981 121d 💬 8