Home
Blog
Google Search Is a Legacy Product
Updated
Dot Net Perls

Google Search Is a Legacy Product

Some months ago I stopped using Google Search. I had noticed the quality of the results were terrible, and there were ads and shopping sections everywhere. It would rewrite my queries so that they were more profitable to Google. It was no longer useful to me, so I moved on to other things.

With the introduction of ChatGPT, LLMs became an option to answer queries about the world. But eventually I figured out that LLMs can be run locally, and when you do this, you can keep all your queries local to your own computer. No external website gets any information about a local LLM query.

Both Google and OpenAI (along with many other companies) release open-weights LLMs like Gemma and GPT-OSS. These can be run on relatively new computers with consumer-grade GPUs. When run, these LLMs do not insert shopping links and ads everywhere—they do not rewrite my query with the intent to sell me stuff.

For current events and weather, a search engine is still useful, but I have found Bing is approximately as good as Google on most queries, and for the ones where there is a quality difference, Bing is the one that tends to be superior. I guess tech products do not last forever—consider Yahoo Search and Facebook. Google Search is a legacy product—one so weighted down by its past successes, and its owner's constant need for revenue, that it has become unusable now.

Dot Net Perls is a collection of pages with code examples, which are updated to stay current. Programming is an art, and it can be learned from examples.
Donate to this site to help offset the costs of running the server. Sites like this will cease to exist if there is no financial support for them.
Sam Allen is passionate about computer languages, and he maintains 100% of the material available on this website. He hopes it makes the world a nicer place.
An RSS feed is available for this blog.
Home
Changes
© 2007-2025 Sam Allen