Hacker News
Napster Is Now Making AI-Powered 'Digital Twins' of Teachers
Article URL: https://gizmodo.com/napster-is-now-making-ai-powered-digital-twins-of-teachers-2000814010
Comments URL: https://news.ycombinator.com/item?id=49759702
Points: 1
# Comments: 0
Data Centers Are Breaking the Power Grid [video]
Article URL: https://www.youtube.com/watch?v=X71le3av1So
Comments URL: https://news.ycombinator.com/item?id=49759655
Points: 4
# Comments: 1
Partnering with Accenture on Embedded Evaluation
Article URL: https://www.anthropic.com/news/accenture-embedded-evaluation
Comments URL: https://news.ycombinator.com/item?id=49759647
Points: 2
# Comments: 0
Taking Out the Trash in Postgres
Article URL: https://www.dbos.dev/blog/scaling-deletions-in-postgres
Comments URL: https://news.ycombinator.com/item?id=49759636
Points: 1
# Comments: 0
The last IMO problem AI could not solve [video]
Article URL: https://www.youtube.com/watch?v=Nbwv5wHQoj0
Comments URL: https://news.ycombinator.com/item?id=49759627
Points: 3
# Comments: 0
Can Two Friends Complete a Game No One Has Ever Finished?
Article URL: https://www.nytimes.com/2026/09/18/world/europe/campaign-for-north-africa-game.html
Comments URL: https://news.ycombinator.com/item?id=49759620
Points: 2
# Comments: 1
Why a Vat API Needs More Than a Rate Lookup?
Article URL: https://vat-engine.app/blog/why-a-vat-api-needs-more-than-a-rate-lookup
Comments URL: https://news.ycombinator.com/item?id=49759563
Points: 1
# Comments: 0
Iran and China Create Autonomous A.I. Influence Campaigns
Article URL: https://www.nytimes.com/2026/09/18/technology/iran-china-autonomous-ai-influence-campaigns.html
Comments URL: https://news.ycombinator.com/item?id=49759525
Points: 3
# Comments: 1
Uncle Bob Martin's UML Tool to Manage Grok AI Agents
Article URL: https://github.com/unclebob/uml-viewer
Comments URL: https://news.ycombinator.com/item?id=49759501
Points: 1
# Comments: 0
Astra broke a yet unsolved German Army Enigma message from 1941
Article URL: https://mvueh-enigma-solved.carterl.chatgpt.site/
Comments URL: https://news.ycombinator.com/item?id=49759492
Points: 2
# Comments: 1
Hooli billboard off of 101
Article URL: https://twitter.com/MikeIsaac/status/2100691714713509986
Comments URL: https://news.ycombinator.com/item?id=49759034
Points: 1
# Comments: 0
Anthropic's new Claude Code feature could drain your plan before lunch
Article URL: https://thenewstack.io/claude-code-parallel-projects/
Comments URL: https://news.ycombinator.com/item?id=49759033
Points: 1
# Comments: 0
Using CSS media queries to target monochrome e-paper
Article URL: https://geastack.com/blog-same-app-color-and-e-paper
Comments URL: https://news.ycombinator.com/item?id=49759020
Points: 1
# Comments: 0
Show HN: OnPanda – Steer LLMs and agents at the token level
I built onPanda – an interactive tool for token visualization & control, model inspection and data annotation.
onPanda is designed for hackers, power users, curious minds, and engineers. Its UI is built for deep exploration and efficient data annotation.
- The core loop is simple: hover over a token → click an alternative or edit freely → continue generation. You can edit every part of model output exposed by onPanda, including reasoning and tool calls. - Edit prompts directly, branch tool calls, and use a tree structure to record branch history. This makes onPanda useful for model inspection and prompt engineering. - Support multiple modalities, including images, video, and audio; use tool calls and connect MCP servers to perform tasks in real environments. - Connect popular harnesses such as Claude Code, Codex, and OpenCode to execute tasks. Explore and compare their tool sets, system prompts, skills, and memory mechanisms. - onPanda includes a built-in browser-agent, an agent that runs in the user's browser without installation. It uses the browser as its harness and provides JavaScript execution, information retrieval, interface interaction, multimedia I/O, local file access, and persistent memory. - onPanda stands for on-Policy Alignment Data Annotator. - As an annotation tool, onPanda efficiently labels on-policy data. Its token-level correction format also provides fine-grained supervision with precise positions and naturally paired positive–negative samples. - We believe these unique properties will make token-level correction a highly efficient and practical paradigm for future LLM alignment. - Our paper and benchmark for token-level correction: https://on-panda.github.io/research/
I have been building onPanda since Sept 2024, and it took two years for it to gradually enrich its functionality and ease of use. Any feedback and evaluation are welcome.
Try it online (works on mobile): https://onpanda.diyer22.com/
GitHub repo for self-hosting: https://github.com/on-panda/on-panda
Detailed introduction on X: https://x.com/diyerxx/status/2101020850405462041
Comments URL: https://news.ycombinator.com/item?id=49759013
Points: 1
# Comments: 0
Running PyTorch natively on TPU [video]
Article URL: https://www.youtube.com/watch?v=k0o1p4plC98
Comments URL: https://news.ycombinator.com/item?id=49759009
Points: 1
# Comments: 0
Base Labs launches an open-weight AI safety partnership with Hugging Face
Advertising is coming to AI chatbots, and it could influence the answers you get
Article URL: https://techxplore.com/news/2026-09-advertising-ai-chatbots.html
Comments URL: https://news.ycombinator.com/item?id=49758974
Points: 1
# Comments: 0
Speaking with the Mind – Neuralink [video]
Article URL: https://www.youtube.com/watch?v=_j806JHhCRo
Comments URL: https://news.ycombinator.com/item?id=49758970
Points: 2
# Comments: 0
Avoiding the Dangers of AI Code with Formal Specifications and Tests
Anthropic sets up biology lab as it ramps AI drug program
Article URL: https://www.reuters.com/world/anthropic-quietly-sets-up-biology-lab-it-ramps-ai-drug-program-2026-09-18/
Comments URL: https://news.ycombinator.com/item?id=49758943
Points: 1
# Comments: 1
