Experimental News Clipping Site

Tag: software development

  • Simon Willison’s Weblog: Gemini 2.5 Pro Preview pricing

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Apr/4/gemini-25-pro-pricing/ Source: Simon Willison’s Weblog Title: Gemini 2.5 Pro Preview pricing Feedly Summary: Gemini 2.5 Pro Preview pricing Google’s Gemini 2.5 Pro is currently the top model on LM Arena and, from my own testing, a superb model for OCR, audio transcription and long-context coding. You can now pay for it! The new…

  • Unit 42: OH-MY-DC: OIDC Misconfigurations in CI/CD

    —

    by

    Kurt Seifried
    in

    Source URL: https://unit42.paloaltonetworks.com/oidc-misconfigurations-in-ci-cd/ Source: Unit 42 Title: OH-MY-DC: OIDC Misconfigurations in CI/CD Feedly Summary: We found three key attack vectors in OpenID Connect (OIDC) implementation and usage. Bad actors could exploit these to access restricted resources. The post OH-MY-DC: OIDC Misconfigurations in CI/CD appeared first on Unit 42. AI Summary and Description: Yes Summary: The…

  • Simon Willison’s Weblog: smartfunc

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Apr/3/smartfunc/ Source: Simon Willison’s Weblog Title: smartfunc Feedly Summary: smartfunc Vincent D. Warmerdam built this ingenious wrapper around my LLM Python library which lets you build LLM wrapper functions using a decorator and a docstring: from smartfunc import backend @backend(“gpt-4o") def generate_summary(text: str): """Generate a summary of the following text: """ pass summary…

  • Simon Willison’s Weblog: Quoting Nolan Lawson

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Apr/3/nolan-lawson/#atom-everything Source: Simon Willison’s Weblog Title: Quoting Nolan Lawson Feedly Summary: I started using Claude and Claude Code a bit in my regular workflow. I’ll skip the suspense and just say that the tool is way more capable than I would ever have expected. The way I can use it to interrogate a…

  • Slashdot: 95% of Code Will Be AI-Generated Within Five Years, Microsoft CTO Says

    —

    by

    Kurt Seifried
    in

    Source URL: https://developers.slashdot.org/story/25/04/02/1611229/95-of-code-will-be-ai-generated-within-five-years-microsoft-cto-says?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: 95% of Code Will Be AI-Generated Within Five Years, Microsoft CTO Says Feedly Summary: AI Summary and Description: Yes **Summary:** Microsoft CTO Kevin Scott emphasizes a transformative evolution in software engineering driven by AI, predicting that AI will generate 95% of code in five years. He suggests that this…

  • Scott Logic: Making Sense of the AI Developer Tools Ecosystem

    —

    by

    Kurt Seifried
    in

    Source URL: https://blog.scottlogic.com/2025/04/01/making-sense-of-the-ai-developer-tools-ecosystem.html Source: Scott Logic Title: Making Sense of the AI Developer Tools Ecosystem Feedly Summary: The AI developer tooling landscape has rapidly expanded from simple autocomplete to a complex ecosystem of assistants, agents, and AI-first environments. In this post, I propose a practical classification based on how AI is positioned within your workflow—from…

  • Hacker News: LLM providers on the cusp of an ‘extinction’ phase as capex realities bite

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/03/31/llm_providers_extinction/ Source: Hacker News Title: LLM providers on the cusp of an ‘extinction’ phase as capex realities bite Feedly Summary: Comments AI Summary and Description: Yes Summary: Gartner predicts a significant consolidation in the large language model (LLM) market, highlighting the challenges faced by providers due to high costs and competition. With generative…

  • Simon Willison’s Weblog: Pydantic Evals

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Apr/1/pydantic-evals/#atom-everything Source: Simon Willison’s Weblog Title: Pydantic Evals Feedly Summary: Pydantic Evals Brand new package from the Pydantic AI team which directly tackles what I consider to be the single hardest problem in AI engineering: building evals to determine if your LLM-based system is working correctly and getting better over time. The feature…

  • Simon Willison’s Weblog: debug-gym

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Mar/31/debug-gym/#atom-everything Source: Simon Willison’s Weblog Title: debug-gym Feedly Summary: debug-gym New paper and code from Microsoft Research that experiments with giving LLMs access to the Python debugger. They found that the best models could indeed improve their results by running pdb as a tool. They saw the best results overall from Claude 3.7…