Would you mind testing this tool I'm writing? I'm building it as a proxy for some streamlit apps and MCP but you can try and put any webapp/API behind it. Do raise issues if you find any.
I got my reader going by running Caddy and pointing my browser at: http://localhost:8080/reader.html
Imported about 750 feeds. Still buggy.
A lot of fiddling. Have to run PHP, PHP-FHM, install CURL, and messed around with configuration files.
Also needs a PHP proxy script to run alongside the HTML and ensure URI encoding.
Not easy done but can now disable CORS Unblock in the browser. Yet now these extra things have to run as services all the time.
Sidepage doesn't seem quite right for me at this stage but thanks for the ideas. It looks like it could do the same job, though. As long as an AI can provide detailed instructions and troubleshooting, it'll lower the barriers-to-entry.
I think the future may well be a modified browser with CORS Unblocking built-in (or some type of proxy alternative.) Have it offer 1000s of free "page-apps" from the get-go. Easy development and ubiquitous platform is the key. Offline button clearly marked and traffic/bandwidth data collection and window.
P2P and micropayments stuff could be interesting.
Overall, the downfall of feeds has either pulled people into the walled gardens or pushed them offline completely. Look at the new Commodore minimalist phone.
The intro is brilliant, the tech and the math is average(you can probably find way better math explanations here on HN). Check out the interview around 22 min mark for something REALLY cool!
No affiliation, I just liked the way they have covered the tech.
I'm not sure about the rebranding of products, but some of the features like the learning path creation and coding challenges definitely look interesting.
If this leads to SO regaining some of its popularity, I'm all for it!
I've bought a bunch of Philips products over the years, and always hated the fact that a simple thing like a charger breaking would lead to throwing away the entire thing- especially grooming products like trimmers. This release of 3D printable models definitely feels like a step in the right direction.
I think being snarky about little things isn't really promoted on HN- it's the first guideline for commenting here. Be kind and try to answer the question if you do have an answer.
Cognitive Search is nowhere as good as a 'pure' vector DB. Behind the scenes, it's a managed elasticsearch/opensearch with some vector search capabilities. The 'AI' implementations I've done with Cognitive Search always boil down to hybrid(vector+fts) text search.
In context of RAG, the goal is not to have a pure vector DB but to have all the relevant data that we can gather for a user's prompt. This is where Cognitive Search and other existing DBs shine because they offer a combination of search strategies. Hybrid search on Cognitive Search performs both full text and vector queries in parallel and merges results which I find a better approach. Further, MS is rebranding Cognitive Search as Azure AI Search to bring it more in line with the overall Azure AI stack including Azure OpenAI.
Cognitive Search already contains hybrid search (vector + BM25 + custom ML reranking) and they use chunks of 2048 tokens with a custom tokenizer. So it should be now better than most vector DBs. One could probably make something better by using some version of SPLADE instead of BM25 but their secret sauce lies in their custom ML model for reranking that gives them the largest search performance boost.
reply