• @[email protected]
    link
    fedilink
    191 year ago

    When you use AI features, the IDE needs to send your requests and code to the LLM provider. In addition to the prompts you type, the IDE may send additional details, such as pieces of your code, file types, frameworks used, and any other information that may be necessary for providing context to the LLM.

    Doesn’t sound like it gives you much transparency or control over the data it sends no matter which feature you use. Sadly not usable at my job then.

    • @[email protected]
      link
      fedilink
      81 year ago

      That’s a bummer. We’re strictly regulated and stuff like this needs to be self hosted or we can’t use it

      • @[email protected]
        link
        fedilink
        51 year ago

        I worked for regulated companies too, I suspect that most companies would forbid such tools even if it’s not a dependency to build the software, especially if the source code is sent to random people. IMHO, every tool should be stored locally (e.g. on a proxy server) to make sure that the whole project can be recreated in a few minutes should something bad happens (or from scratch in a CI). As long as AIs rely on private companies on the internet, I wouldn’t use those tools.

      • @[email protected]
        link
        fedilink
        21 year ago

        They do say this though “We also plan to support local and on-premises models. For local models, the supported feature set will most likely be limited.”

        This is currently a no go at my place (I asked) but the ai and security folks were interested in that as it would allow on-prem/private cloud usage as well as the possibility of using targeted models instead of a generic one.

        For example, in the comments on their announcement they confirm they are looking at Azure AI support.