Best of OpenAI — November 2025

  1. 1
    Article
    Avatar of bhsp8lwj2nc2bnkkiyg3zAishwary Gupta·26w

    OpenAI dropped a cookbook on Self-Evolving Agents

    OpenAI released a comprehensive cookbook featuring open-source examples and tutorials for building applications with their API. The collection covers fundamental API usage through advanced implementations including fine-tuning, RAG, function calling, vector databases, multimodal applications, and self-evolving agent development. Practical guides span GPT models, embeddings, image generation, speech processing, and platform integrations.

  2. 2
    Article
    Avatar of colkgirlCode Like A Girl·28w

    I Overcame Inertia with a Weekend Project

    A developer shares their experience overcoming creative inertia by building a simple AI-powered meal planning tool in 4 hours. Using Streamlit, Python, and OpenAI, they created an MVP that generates weekly meal plans and grocery lists. The project served as a catalyst to break through mental resistance and reignite motivation for side projects, demonstrating how focusing on completion rather than effort can help overcome procrastination.

  3. 3
    Video
    Avatar of fireshipFireship·26w

    Did Google just kill OpenAI?

    Google released Gemini 3 Pro, which topped major AI benchmarks and prompted companies like Anthropic to switch from Claude. The release boosted Google's stock by 6% to an all-time high. Google also unveiled anti-gravity, an agentic coding platform built on technology from the acquired Windsurf team, competing with other AI-powered development tools like Cursor and their own idx/Firebase Studio.

  4. 4
    Article
    Avatar of phProduct Hunt·29w

    Helicone AI: Open-source LLM Observability for Developers

    Helicone is an open-source platform that provides observability and monitoring for AI applications using large language models. It offers a unified API gateway that consolidates access to 100+ models from multiple providers through a single API key, with zero markup fees. Key features include automatic failover, built-in caching, custom rate limits, real-time analytics, and OpenAI SDK compatibility. The platform addresses common challenges like provider outages, rate limiting, and managing multiple API integrations while providing full visibility into performance and costs.

  5. 5
    Article
    Avatar of wheresyouredWhere's Your Ed At·28w

    Where Is OpenAI's Money Going?

    OpenAI reported $12 billion in losses for Q3 2025 according to Microsoft's SEC filings, raising questions about the company's financial sustainability. Despite CEO Sam Altman claiming revenues "well more" than $13 billion for 2025, analysis suggests actual revenue may be closer to $8 billion. The company has committed to massive cloud computing deals totaling over $1.4 trillion over 8 years with AWS, Oracle, CoreWeave, and Microsoft Azure. By 2027, monthly compute costs alone could exceed $11 billion, while the company employs only 3,000 people compared to Meta's 78,000 and Microsoft's 200,000. Financial discrepancies between reported figures and actual spending patterns suggest OpenAI's inference costs may be significantly higher than publicly stated.

  6. 6
    Article
    Avatar of newstackThe New Stack·29w

    OpenAI Co-Founder: AI Agents Are Still 10 Years Away

    OpenAI co-founder Andrej Karpathy predicts AI agents are still a decade away from replacing human workers, despite recent progress with large language models. He argues the industry is over-hyping current capabilities, citing issues like lack of multimodal functionality, continual learning, and the significant demo-to-product gap. Karpathy draws from his experience leading Tesla's self-driving efforts to illustrate how difficult it is to move from working demos to production-ready systems. He's now focusing on AI education through Eureka Labs, releasing projects like nanochat to help developers understand LLM implementation from the ground up.

  7. 7
    Video
    Avatar of t3dotggTheo - t3․gg·28w

    GPT-5.1 is built for normies

    GPT-5.1 represents a shift toward consumer-focused AI with improved conversational tone, customizable personalities, and enhanced safety guardrails. The release prioritizes warmth and accessibility over developer features, with API access delayed. Testing reveals better mental health safeguards and reduced sycophancy compared to GPT-4, though the model's personality options and emoji-heavy responses may not appeal to technical users. The instant variant shows adaptive reasoning that adjusts token usage based on query complexity, while safety evaluations demonstrate meaningful improvements in handling sensitive content.

See all OpenAI archives