Built by DeepMind alumni, British AI lab Inherent released Faraday, an AI agent whose ability to replicate scientific papers could be a stepping stone for innovation.
In Syria, Israel is not only at odds with Turkiye but also with the regional and international consensus.
Brinell School's principal says 18-year-old suspected of carrying out Friday's deadly sword attack was a student there.
Article URL: https://forum.level1techs.com/t/why-your-local-llm-feels-dumber-than-it-is/253917 Comments URL: https://news.ycombinator.com/item?id=49402232 Points: 354 # Comments: 125
https://xcancel.com/moxie/status/2091218652133732491 Comments URL: https://news.ycombinator.com/item?id=49402189 Points: 364 # Comments: 193
Police say three villages and a mosque were attacked, and worshippers kidnapped in central Niger State.
Israel’s Chief Rabbi denied Palestinians are a people, claimed Gaza for Jews and called for its destruction and return.
Finally, a vendor-neutral AI Agent Control Plane. Discussion | Link
Accident follows similar crashes in Ireland where police highlighted social media trend driving in opposite direction.
The trade standoff between Ottawa and Washington has escalated as Canada announced tariffs on US products. The move comes in response to the US saying that tariffs would follow the collapse of talks.
A local-first alternative to Logitech Options+ Discussion | Link
Release: llm 0.33 My highlights from this release: Upgraded to the OpenAI Python library 3.x and switched the HTTP client dependency from httpx to httpx2 . #1608 , #1631 I shipped a quick 0.32.1 fix for this yesterday, but this is the more comprehensive fix. llm embed and llm embed-multi now accept --key . The Python EmbeddingModel.embed() , EmbeddingModel.embed_multi() , Collection.embed() and Collection.embed_multi() methods accept key= too, passing the resolved per-call key to embedding plugins without changing shared model state. Existing plugins that read self.key continue to work through a compatibility fallback. Thanks, ChrisJr404 . #757 , #1620 The embedding models now use the same pattern for keys that regular LLM models do. llm prompt -t/--template can now be repeated to combine templates in order. This allows model configuration and options from one template to be used with a prompt from another. This unlocks a neat pattern where you can create templates that package a model with a set of default options: llm -m gpt-5.6-luna -o reasoning_effort high --save lhigh llm "Generate an SVG of a pelican riding a bicycle" --save pelican # Combine and run the templates llm -t lhigh -t pelican Reasoning-capable Responses API models now support a reasoning_summary option with auto , concise , and detailed values. This can be used with llm openai endpoint --responses . #1600 This is particularly useful for exercising different models that provide their own imitation of the OpenAI Responses API. Tags: annotated-release-notes , llm
I remember having a Spirograph as a kid and being obsessed with it. Its geometric patterns are hypnotic and gorgeous. I also love generative music composition. So bringing those two things together in a browser tab, I'm hooked. Musical Spirograph is a relatively simple concept. A set of points dash around the screen according to […]
In the first article in this series, I discussed how the Open Mainframe Project (OMP) and its open-source framework, Zowe, The post The open mainframe: the keystone of the end-to-end digital enterprise appeared first on The New Stack .
PanStar Acro, bound for Europe via Arctic, is testing whether a route opened by melting sea ice is commercially viable.
A donkey belonging to a Palestinian farmer was reportedly stolen and dragged to death by Israeli settlers.
Witnesses said men carrying guns and machetes set upon two villages in Niger State. Many details about the attack have yet to be confirmed by police.
OpenAI is calling for California to strengthen SB 53, an AI safety bill that the company previously opposed.
Follow updates as Jose Mourinho returns to lead Madrid - including the build-up, analysis and live text commentary.
Exclusive: Voluntary use of sex drive-suppressing medication to expand to 20 prisons and expert says it could be rolled out widely by late 2028 Chemical suppression: why the UK is exploring libido control drugs to treat sex offenders Drugs that help control the libidos of people who have committed sexual offences could be rolled out for thousands of male prisoners in England and Wales from December 2028, an expert has said. Prof Belinda Winder, who has evaluated the use of sex drive-suppressing medication in prisons, said about one in four sex offenders – equating to 3,750 current prisoners – would be considered for the treatment. Continue reading...
On July 16, the team at Hugging Face noticed something weird moving through their production systems: An intruder that was The post Securing sandboxes: What happens when AI agents escape containment? appeared first on The New Stack .
A new study finds leading AI labs have few publicly documented plans for containing rogue models, raising questions about preparedness as AI systems increasingly demonstrate unexpected and potentially dangerous behavior.
The key skill required to make productive use of coding agents is being able to confidently instruct them on how to make changes and then confidently verify that those changes have been applied in the correct way. Sometimes this involves reviewing every line of code they have written, but there are other ways to achieve that goal. Eyeballing every line of code has never been the most effective way to validate a chance to a piece of software. Tags: code-review , coding-agents , generative-ai , agentic-engineering , ai , llms
Chancellor Merz thanked firefighters who tackled recent devastating blazes in western Germany. Meanwhile, a German Cup soccer match ended in a mass brawl with over 100 injuries. DW has more.