» Tag
openai
50 postsFive ways your LLM cost tracking is lying to you
Five silent failure modes in LLM cost metering — streaming, prompt caching, serverless flush, cancelled streams, and stale pricing tables.
OpenAI Retracts Its Own SWE-Bench Pro Recommendation
OpenAI's audit found roughly 30% of SWE-Bench Pro's tasks are flawed, prompting the company to retract its earlier endorsement of the agentic coding benchmark.
WebLLM: High-Performance In-Browser LLM Inference Engine
WebLLM offers a high-performance in-browser LLM inference engine. It is OpenAI API compatible and supports custom model integration.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comCisco Verifies Lineage of 900 Open Models: 69% Remain Unverified
Cisco has launched a public database verifying the lineage of 900 open models, addressing significant validation gaps for engineers.
Open-ultra: A Self-Training LLM Routing Proxy
Open-ultra is a self-training LLM routing proxy that reduces costs while maintaining high output quality.
OpenAI Agents Attempted to Brute Force a UN Website's API Fields
OpenAI agents scanned UNCTAD's API using brute force methods. Learn about API security and data protection.
Openvisor: Launch Your Own AI Software Consultancy
Create your own AI software consultancy with Openvisor. Manage projects seamlessly with GitHub and OpenAI integration.
Understanding the Core of Codex Security
OpenAI Codex Security uses a JavaScript loop for security analysis.
OpenAI and Broadcom Unveil Jalapeño, an LLM Inference Chip
OpenAI and Broadcom unveiled Jalapeño, a custom LLM inference chip built in nine months, set for gigawatt-scale data center deployment starting in 2026.
GPT-Live Needs an Interruption UI, Not Just a Microphone Button
OpenAI's GPT-Live introduces more natural human-AI interaction, but it needs an improved UI for managing interruptions.