←Search results

Search “OpenAI”

By relevance · Total 3712 results Clear search

Friday

  3. TensorZero Engineering Blog

    TensorZero Engineering Blog: List of Articles on Open-Source LLM Infrastructure

    The TensorZero engineering blog has compiled multiple articles on its open-source LLM infrastructure, the latest being "Even (very) noisy LLM evaluators are useful for improving AI agents" by Alan Mishler on May 12, 2026. Previous articles covered topics such as hidden costs of LLM APIs, automated AI engineers, bandit adaptive experimentation in the LLM Gateway, OpenAI RFT evaluation, 5-30x cheaper distilled inference, and reverse engineering Cursor's LLM client.

    Matched fieldsSummary、Body

    #engineering#English text is being prepared.
  13. TechCrunch AI

    AI leaderboard Arena completes $200 million Series B funding at a $3.1 billion valuation

    AI model crowdsourced leaderboard Arena announced the completion of a $200 million Series B funding round at a $3.1 billion valuation, led by Lightspeed Venture Partners and Khosla Ventures, with participation from Salesforce Ventures, 01 Advisors, Dell Technologies Capital, Endeavor Catalyst, a16z, Felicis, and others. The company said its annualized revenue reached $100 million in June, while at the time of its Series A funding in January it was valued at $1.7 billion with $30 million in annualized revenue, meaning its valuation nearly doubled in about ten months. Arena also added an alignment category to its leaderboard, ranking models by issues such as unauthorized actions, misattribution, and falsely completing tasks; currently multiple OpenAI models occupy the top of the preliminary alignment leaderboard, with Claude Opus 5.5 and Claude Fable ranked sixth and ninth, respectively.

    at the time of its Series A funding in January it was valued at $1.7 billion with $30 million in annualized revenue, meaning its valuation nearly doubled in about ten months. Arena also added an alignment category to its leaderboard, ranking models by issues such as unauthorized actions, misattribution, and falsely completing tasks; currently multiple OpenAI models occupy the top of the preliminary alignment leaderboard, with Claude Opus 5.5 and Claude Fable ranked sixth and ninth, respectively.

    Matched fieldsSummary、Body

    #tech-media#Industry news#Evaluations / benchmarks#Safety / alignment
  16. Arena

    Arena Completes $200 Million Series B Funding, Releases Alignment Index

    Arena announced the completion of a $200 million Series B funding round at a valuation of $3.1 billion, and simultaneously released the Alignment Index, which is based on 90K+ real agent sessions covering 27 models and evaluates the safety and alignment of AI agents across three signals: Unauthorized Action, False Attribution, and Deceptive Completion. The leaderboard shows that OpenAI's GPT-6.1-Sol ranks first with a score of 87.9, Claude-Opus-5.5 scores 83.2, and Grok-4.7 scores 82.7; OpenAI's rates for the three signals are 0.89%, 1.98%, and 2.34%, respectively.

    at a valuation of $3.1 billion, and simultaneously released the Alignment Index, which is based on 90K+ real agent sessions covering 27 models and evaluates the safety and alignment of AI agents across three signals: Unauthorized Action, False Attribution, and Deceptive Completion. The leaderboard shows that OpenAI's GPT-6.1-Sol ranks first with a score of 87.9, Claude-Opus-5.5 scores 83.2, and Grok-4.7 scores 82.7; OpenAI's rates for the three signals are 0.89%, 1.98%, and 2.34%, respectively.

    Matched fieldsSummary

    #editorial#Industry news#Safety / alignment#Agents

Thursday