A local server that delivers existing Markdown/Obsidian documents to coding agents via CLI, HTTP, and MCP without modification.
Researchers identified a specific activation direction that toggles between disclaimer and experiential self-reports in open-source LLMs.
The Emacs package agent-shell, based on the ACP protocol, has been released, enabling control of 19 coding agents through a single UI.
This article derives policy gradient methods for LLMs, explaining how REINFORCE evolves into GRPO through baseline variance reduction and addressing the gradient bias caused by inference engine mismatches.
New filings in Authors Guild v. OpenAI include internal communications where executives acknowledged using LibGen and discussed deleting evidence under 'Project Clear'.
Serving 100M daily active users for Meta's Muse agent requires approximately 1–2 GW of average power, with inference accounting for the vast majority of demand.
Julia-1 is a 144.3 million parameter multilingual encoder designed for CPU-only execution, capable of classification, ranking, and binary question answering.
Figure achieves an average household task success rate of 56% across 30 unseen homes by pre-training on human behavior data
A router trained on RouteLLM data achieved 0.84 AUC but dropped to 0.838 when labels were shuffled, indicating it learned task identity rather than item difficulty.
Atlas is a Tauri-based desktop application that manages parallel coding agents like Claude Code and Codex by linking commits to session contexts and sharing memory across tools.
A simulation shows adding call options to annual GPU rentals raises average costs slightly but cuts worst-case hourly rates from $10.91 to $7.20.
Ember-1 is a research preview model built on Kimi K3 that reportedly generates 40% fewer tokens than its base model.
The new MOPD-based solution reduced repetition rates significantly at a cost of approximately $90,000, compared to an estimated $2.31 million for a full MixRL restart.
A community-developed Jinja template for GPT-OSS fixes a bug in the widely used Unsloth version that caused the model to drop final answers when reasoning traces were present in chat history.
The DSec platform supports over 380,000 concurrent sandboxes and 5,000 creations per second to enable efficient reinforcement learning for LLM agents.
The 8B parameter model achieves competitive results with Qwen-Image 20B on specific benchmarks while using a single backbone for both generation and understanding.
Existing Claude Pro and Max subscribers can claim a one-time credit of $100 or $250 respectively for Claude Code cloud sessions by October 7.
Internal papers reveal Oxford University allowed OpenAI to use 125,000 scans of Bodleian Library texts for AI training, a use case not explicitly stated in the original public announcement.
Opus 5.5 scores 58 on Artificial Analysis Intelligence Index but costs $5.98 per task compared to GPT-6 Astra's $3.26 due to higher token usage.
AI Briefing