Login
Show HN: Meteor shower, planet alignment, eclipse kit
(lifesprites.com) by jmtrevarton | view | 18 comments
Finding Alignment by Visualizing Music in Rust
(positron.solutions) by positron26 | view | 0 comments
64-Bit Misalignment
(jordivillar.com) by thunderbong | view | 1 comments
Is AI Really Alignment Faking?
(iacgm.com) by iacgm | view | 1 comments
Show HN: Thermodynamic Alignment Forces Gemini Thinking into "Burn Protocol"
(github.com) by CodeIncept1111 | view | 7 comments
Natural emergent misalignment from reward hacking in production rl [pdf]
(assets.anthropic.com) by neapolisbeach | view | 0 comments
Aligning brains into a shared space improves their alignment with LLMs
(nature.com) by stevenjgarner | view | 0 comments
Anthropic Has Some Alignment Problems
(thezvi.substack.com) by paulpauper | view | 0 comments
AI Alignment as a Thought-Terminating Cliche
(borretti.me) by meetpateltech | view | 0 comments
OpenAI Hacks Hugging Face, What Happened, Alignment and Paper Clips
(stratechery.com) by swolpers | view | 0 comments
Safety and alignment in an era of long-horizon models
(openai.com) by Wingy | view | 0 comments
Secure Linear Alignment of Large Language Models
(arxiv.org) by walterbell | view | 1 comments
What if AI alignment is a skill, not a state?
(12gramsofcarbon.com) by theahura | view | 0 comments
Show HN: Chatbot Without Safety Alignment
(coralflavor.com) by JohnLins | view | 0 comments
Who Owns Alignment?
(backnotprop.substack.com) by ramoz | view | 0 comments
Ask HN: Is the absence of affect the real barrier to AGI and alignment?
by n-exploit | view | 1 comments
Alignment Research Blog
(alignment.openai.com) by ironyman | view | 0 comments
Values.md – file format for personal ethical alignment
(values.md) by georgestrakhov | view | 0 comments
Alignment: The Invisible Force That Makes Everything Work
(itrevolution.com) by mooreds | view | 0 comments
Wargaming AI Alignment
(twitter.com) by JL-Akrasia | view | 2 comments
Show HN: Alignmenter – Measure brand voice and consistency across model versions
(alignmenter.com) by justingrosvenor | view | 2 comments
TelUI 1.2: TelUI with fun alignments
by telui | view | 0 comments
Astra and Fable still hack on simple variants of alignment evals from early 2025
(goodhartlabs.com) by dnfv | view | 0 comments
Astra and Fable still hack on simple variants of alignment evals from 2025
(lesswrong.com) by yurivish | view | 0 comments
Where Alignment Becomes the Work
(medium.com) by gps372 | view | 0 comments
OpenAI: We monitor internal coding agents for misalignment
(openai.com) by lukaspetersson | view | 0 comments
HF hack alignment: make agents more selfish
(nonlineartransform.substack.com) by program_whiz | view | 0 comments
An Interview with OpenAI President Greg Brockman About Astra and Alignment
(stratechery.com) by swolpers | view | 0 comments
Natural emergent misalignment from reward hacking
(anthropic.com) by tosh | view | 0 comments
Consider that alignment may not be possible
(12gramsofcarbon.com) by theahura | view | 0 comments
Improving our alignment and security efforts
(anthropic.com) by reasonableklout | view | 0 comments
Improving our alignment and security efforts
(anthropic.com) by jbegley | view | 0 comments
Improving our alignment and security practices
(anthropic.com) by surprisetalk | view | 0 comments
Automated researchers can reliably mitigate alignment failures
(anthropic.com) by EvgeniyZh | view | 0 comments
Automated Researchers Can Reliably Mitigate Alignment Failures
(alignment.anthropic.com) by isomorphic_duck | view | 0 comments
Group size effects and collective misalignment in LLM multi-agent systems – PNAS
(pnas.org) by Anon84 | view | 0 comments
Multiple sequence alignment using WebGPU
(github.com) by ag4349 | view | 1 comments
AI Alignment as a Thought-Terminating Cliche
(borretti.me) by ibobev | view | 0 comments
Value misalignments in X's feed algorithm
(pnas.org) by GolfPopper | view | 0 comments
AI alignment as continuation control: 31,430 frozen trials
(zenodo.org) by rayanpal_ | view | 0 comments
Performative Agreement: the false alignment trap
(hbr.org) by soupspaces | view | 0 comments
Recovering Alignment from Abliterated LLMs
(rjmxtt.co.uk) by rjmxtt | view | 0 comments
AI alignment is a red herring
(interconnected.org) by peteforde | view | 0 comments
Robust AI Security and Alignment: A Sisyphean Endeavor?
(arxiv.org) by joshcsimmons | view | 0 comments
Show HN: Misalignments when using AI for hacking
(blog.vulnetic.ai) by danieltk76 | view | 0 comments
Indirect Lessons from Human Alignment
(dynomight.substack.com) by paulpauper | view | 0 comments
Indirect Lessons from Human Alignment
(dynomight.net) by zdw | view | 0 comments
Indirect Lessons from Human Alignment
(dynomight.net) by surprisetalk | view | 0 comments
Show HN: I turned the AI alignment debate into a strategy game
(bazman88.github.io) by Bazman88 | view | 0 comments
LLMs Can Infer Political Alignment from Online Conversations
(arxiv.org) by Anon84 | view | 0 comments