Source-checked AI news, every morning. Each day brings six articles and one digest on new models from labs worldwide, research, essays, local models and agents, and prompting techniques. Every article ends with a verification table that links the primary sources.
How we work · Archive · RSS feed · For AI assistants · Slovenské vydanie
The German-English reasoning model ships with Apache-2.0 weights and serving instructions. Its small active parameter count still leaves a large memory requirement.
A controlled preprint separates detecting an activation change from reporting its location. The experiment uses fixed input text and scores answers without an AI judge.
A small trained intervention sharply improves Qwen3-8B on synthetic reference chains. The preprint traces the change to how middle layers pass information between lines.
The Ollama-based project adds voice input and everyday document tools. Its published benchmark argues that small-model results depend heavily on the surrounding software.
The developer's workflow keeps specifications and decisions in editable Markdown. His argument comes with an open-source implementation, but no comparative benchmark.
His proposal favours automatic shutdown at a budget limit. Removing the limit would require an explicit choice.
Research, projects and discussions beyond today's six articles, with source links and evidence labels.
Spotlight Memory addresses a small region of expandable storage at each step. Percepta reports strong retrieval beyond the models’ training length.
A visual-reasoning study targets the information held between seeing an image and answering a question. Its training method makes those hidden states more sensitive to relevant image changes.
A controlled study separates who generates training answers from how a student model learns. Changing the objective and learning rate explains much of the difference.
Version 2.0 uses two teachers to preserve casual dialogue while improving instruction and tool behaviour. The release includes local weights and explicit tradeoffs.
The maintainers argue that structured tool composition changed their earlier objection to the protocol.