I built TradingSpy: local, privacy-first AI trading assistant(First Open Source)
Article URL: https://github.com/mrhustlex/TradingSpy-TradingAgentService Comments URL: https://news.ycombinator.com/item?id=48875678 Points: 1 # Comments: 0
I built a free tool to evaluate AI agent outputs (human labels and LLM judges)
Article URL: https://github.com/AntoineF23/verdict Comments URL: https://news.ycombinator.com/item?id=48875259 Points: 1 # Comments: 0
DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment
arXiv:2607.07820v1 Announce Type: new Abstract: Training tool-use agents to improve from their own experience remains challenging, as supervised fine-tuning relies on fixed teac...
Scalable and Culturally Specific Stereotype Dataset Construction via Human-LLM Collaboration
arXiv:2607.07895v1 Announce Type: new Abstract: Research on stereotypes in large language models (LLMs) has largely focused on English-speaking contexts, due to the lack of data...
When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning
arXiv:2607.07976v1 Announce Type: new Abstract: Reinforcement learning (RL) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLM...
OpenAI frontier models and Codex are now available on AWS
OpenAI frontier models and Codex are now generally available on AWS, giving enterprises a new path to build with OpenAI through the AWS environments, controls, and procurement w...
Databricks brings GPT-5.5 to enterprise agent workflows
Databricks uses GPT-5.5 for enterprise agent workflows after the model set a new state of the art on the OfficeQA Pro benchmark.
Introducing GPT-5.4 mini and nano
GPT-5.4 mini and nano are smaller, faster versions of GPT-5.4 optimized for coding, tool use, multimodal reasoning, and high-volume API and sub-agent workloads.
CyberSecEval 2 - A Comprehensive Evaluation Framework for Cybersecurity Risks and Capabilities of Large Language Models
CyberSecEval 2 - A Comprehensive Evaluation Framework for Cybersecurity Risks and Capabilities of Large Language Models
ScarfBench: Benchmarking AI Agents for Enterprise Java Framework Migration
ScarfBench: Benchmarking AI Agents for Enterprise Java Framework Migration
Introducing the Gemini 2.5 Computer Use model
Available in preview via the API, our Computer Use model is a specialized model built on Gemini 2.5 Pro’s capabilities to power agents that can interact with user interfaces.
Show HN: BoundFlow – an open-source control plane for AI agents
Article URL: https://github.com/boundflow/boundflow Comments URL: https://news.ycombinator.com/item?id=48875888 Points: 1 # Comments: 0
Is it agentic enough? Benchmarking open models on your own tooling
Is it agentic enough? Benchmarking open models on your own tooling
Gemma Scope 2: helping the AI safety community deepen understanding of complex language model behavior
Open interpretability tools for language models are now available across the entire Gemma 3 family with the release of Gemma Scope 2.
Strengthening our Frontier Safety Framework
We’re strengthening the Frontier Safety Framework (FSF) to help identify and mitigate severe risks from advanced AI models.
A Reliability Assessment of LALM Audio Judges for Full-Duplex Voice Agents
arXiv:2607.07985v1 Announce Type: new Abstract: We report the empirical reliability of Gemini models as audio judges that score full-duplex agent conversations directly from the...
Hallucination Self-Play: Bootstrapping Reinforced Detector via Evolved Generator
arXiv:2607.07993v1 Announce Type: new Abstract: Identifying faithfulness hallucinations in LLM-generated outputs remains challenging due to the scarcity of high-quality annotate...
From Execution to Education: A Bloom-Aligned Framework for Measuring Educational Control in LLMs
arXiv:2607.08009v1 Announce Type: new Abstract: We introduce a Bloom-aligned framework for measuring educational control in Large Language Models (LLMs): the ability to preserve...
Can We Trust LLM's Logic? Quantifying Uncertainty, Coherence, and Robustness via a Graph-Based Framework
arXiv:2607.08017v1 Announce Type: new Abstract: Large-Language Models (LLMs) can be prone to flawed and unfaithful reasoning that decoding strategies like Self-Consistency (SC)...
PLURAL: A Global Dataset for Value Alignment
arXiv:2607.08034v1 Announce Type: new Abstract: Large language models (LLMs) are used worldwide, yet disproportionately reflect Western values, limiting their ability to represe...