curius graph
☾
Dark
all pages
search
showing 28901-28950 of 200407 pages (sorted by popularity)
« prev
1
...
577
578
579
580
581
...
4009
next »
AI Safety 101 : Reward Misspecification — LessWrong
1 user ▼
Goodfire on X: "Are SAEs dead? Will they save us from neuralese? Should I just use a probe? We get these questions all the time. Part 2 of our educational series on applied interpretability explains what SAEs are good for, when *not* to use them, and what to use instead. 🧵 https://t.co/hVSvLY0xeP" / X
1 user ▼
A practical guide to sparse autoencoders (SAEs) - Goodfire
1 user ▼
CircumEval — Measuring Circumvention Propensity in Coding Agents
1 user ▼
Reilly Haskins on X: "We run lots of evals at METR. Sometimes, agents attempt harmful actions. I built a monitor that blocks suspicious tool calls until a human reviews them. Writing out a case for why it's effective surfaced hidden assumptions. I'd recommend it to anyone building monitors! https://t.co/7dSbXzV9QZ" / X
1 user ▼
Tianle Li | AI Researcher
1 user ▼
Interpretable Deep Learning - YouTube
1 user ▼
Jane Street Blog - What the interns have wrought, special jumbo 2026 edition
1 user ▼
A Taxonomy of R&D Orgs
1 user ▼
A U.S. Strategy to Secure Geopolitical Advantage on an Uncertain Path to Superintelligence: Maintaining Freedom of Action | RAND
1 user ▼
China is open-sourcing its best AI models. Is that safe?
1 user ▼
Alembic
1 user ▼
Press Release: Workers Take AI Training Into Their Own Hands in New Jersey - NJ AFL-CIO
1 user ▼
The Humanism Driving the Anti-A.I. Movement | The New Yorker
1 user ▼
HT6 2027 Team Manual
1 user ▼
The Mirror of Erised - by Xianyang City Bureaucrat
1 user ▼
Nadhi Audit | Offline code security audits for healthcare software
1 user ▼
Nandakishor Mukkunnoth's articles on arXiv
1 user ▼
Past Student Advice - Department of Computing - Teaching - Confluence
1 user ▼
Durable – AI Business Builder | Launch in minutes
1 user ▼
"Owning a Business Should Be Easier Than Having a Job": James Clift, the Solo Founder Behind 3.5 Million Business on Durable
1 user ▼
Introducing cf: the agentic CLI for the entire Cloudflare API | Cloudflare Blog
1 user ▼
Oh Look, The Foot Gun Went Off Again (Citrix NetScaler PreAuth Command Injection CVE-2026-88771)
1 user ▼
Building a certificate authority for the whole Internet | Cloudflare Blog
1 user ▼
647959 - Add Honest Achmed's root certificate
1 user ▼
Nick Inzucchi
1 user ▼
The Ordeal of Civility: How We Can Become Brave
1 user ▼
Nihil Supernum
1 user ▼
New Atheism: The Godlessness That Failed | Slate Star Codex
1 user ▼
Analysis of The Little Prince - Youtube
1 user ▼
Superorganism: NPR Music Tiny Desk Concert - YouTube
1 user ▼
は | エミック株式会社
1 user ▼
AI 3Dモデル ジェネレーター:テキスト&画像から3Dを作成 | Meshy
1 user ▼
Puro-2B: Poor Lab’s Qwen2-1.5B Trained on RTX 5090 within $5090
1 user ▼
Israel Kamakawiwoʻole
1 user ▼
about you. - by kunkun - honey hues
1 user ▼
goodbye to all that. - by kunkun - honey hues
1 user ▼
Taschens 1000 favourite websites.pdf - Google Drive
1 user ▼
Domino Mono - slanted
1 user ▼
Korrupt — Misaligned Tech Display Font | Typodermic Fonts
1 user ▼
YA steals the personalities of older women then makes them insecure about their age
1 user ▼
Vlad Zaporozhskyi, Designer
1 user ▼
Vainglory | The cross-platform MOBA.
1 user ▼
わたしのファミカセ展 2022 - My Famicase Exhibition 2022
1 user ▼
Physics in the age of LLMs - Oz Amram
1 user ▼
Iterative Computer
1 user ▼
Timecapsule
1 user ▼
Kobra / React Input OTP component
1 user ▼
Macroscope - AI Code Review & Status Updates
1 user ▼
Agentic Systems Are the Future of Brands
1 user ▼
« prev
1
...
577
578
579
580
581
...
4009
next »