dennis16384

If you give it a real solver to drive and business constraints to operate under, it will do pretty good job (which is to map your business rules to constraints and balanced costs, develop deterministic tests, probabilistic tests, acceptance gates, all boring stuff).

Why this kind of marketing is even allowed?

It's been great even since gemini-3.1-flash-lite, which I heavily use in both complex vertical domain tools calling, plus JS code writing for eval-style dynamic tools. At least in my applications, cost x quality x speed there are simply no alternatives.

It is the core of ClickHouse for example, for many years. Is it secure enough in your opinion?

I had a similar success with Model2Vec static embedder and NER inference (both GGUF, compiled for WASM), ported to plain C from ONNX Runtime.

Wasm size from 30Mb to 300kb and 1.5x speedup. It's definitely worth it for performance or distribution size.

People still complain about 95mb download in 2026. It's literally 2 minutes of 1080p youtube watching.

Why bring server software to edge devices? Because its fucking awesome!

clickhouse?

"With experience and support from" is a nice landing trick!

How do you extract and relate to each other the facts from the documents that require comprehension and not simple similarity matching using common embeddings models?

This is the kind of content we all deserved in 2026, and this is still why I ask during interviews to explain how cookies are represented in HTTP protocol.

Working on https://routing24.com, free route optimization for businesses.

Recently started some agentic features for paid version, and this lead to a side project https://eatmydata.ai - a question-to-sql-to-dashboard builder, where data doesn't get exposed to AI (with bundled in-browser SQLite vector search, NER and many other features).

The latter is open-sourced under MIT: https://github.com/eatmydata-org/eatmydata

Hope they'll move eventually to consumer AI devices

Why would an LLM want to look into the contents, what for?

We have low-cardinality data and yes this is safe to share and required to build an actual query.

Then we have high-cardinality and possibly PII - there’s absolutely no reason to share that data, there’s nothing for LLM to analyse there. Also semantic index (vector search) will find relevant records much faster and more accurately that any chain-of-thoughts just with an LLM-authored search fn call.

Further there are continuous numerical values and there’s not much LLM needs to see in there either. We can say, for example, if you look at data distributions when building your analysis, it can drive your analysis logic, but another point of view here is taht it creates unnecessary bias instead.

Totally. One thing that all major AI vendors are not doing currently is merging server AI with edge devices.

For example, there is no way neither in Claude nor in ChatGPT to run your own WASM or JS or whatever AI produces directly in user's browser context as a tool/skill - there is no call site for that. The only option is remote server-side.

My whole idea was that AI can perfectly write SQL and dashboard code knowing only the shape of your data and not it's contents. With direct upload to vendor now we're forced to share the contents.

Fast response. I can upload Excel/csv and iterate under 10 seconds from question to result. Doing same thing in Claude with 10x less data takes 5 minutes.

Nice, I recently did a similar but much simpler thing and open-sourced it under MIT, maybe some bits and pieced will be useful https://github.com/eatmydata-org/eatmydata

For example, MIT-licensed sqlite vector search extension.

Overall, I have a orchestrator - sql coder - js coder - dashboards, all without backend, running locally in the browser. It's mostly tested on small analysis and question answering with Gemini Flash Lite, and the overall target was speed from question to answer, including data sharing and waiting.

I built a question-to-sql-to dashboard tool for quick data analysis, just to avoid sharing random personal or customer xlsx documents with external AI. Released it as MIT recently:

https://eatmydata.ai/

https://github.com/eatmydata-org/eatmydata

Thanks! Yep will change the UI there.

For the "show me how many people are from Dallas" in AdventureWorks, it really depends on the model.

With `gemini-3.1-flash-lite` for all agents it produces this sql from the first try for $0.0033: ``` SELECT COUNT(DISTINCT ca.CustomerID) as customer_count FROM CustomerAddress ca JOIN ( SELECT a.AddressID FROM vector_search('Address', 'City', 'Dallas', 20) vs JOIN Address a ON a.rowid = vs.rowid WHERE a.City = 'Dallas' ) addr ON ca.AddressID = addr.AddressID ```

and then formats output in Markdown.

I'll bake some default model in later, and more examples. And I guess it needs some default token quota.

I'm working on Routing24 https://routing24.com - we are building free route optimization tool for businesses to plan multi-vehicle multi-stop routes.

Multi-threaded WebAssembly in action for route optimization, all bundled with geocoding, OSM maps and routing, and provided world-wide.

We're adding driver's PWA, saving and sharing of route optimization projects, editing of optimized routes, sharing it with others either for execution or for approval, integrations and AI-assisted data imports, auth flows, support prompts, sales automation and all that boring stuff.

Thanks! I haven't figured out the commercial part yet, but plan to have forever fee tier in the future too.

I keep working on Routing24 https://routing24.com, a free route optimization tool for businesses.

It's been approx. an year since we are up and running, and we helped 100+ businesses in the US and world-wide to understand the value and savings of automated route planning, and prepared tens thousands of optimized routes for companies operating from 1 to 50 vehicles. All this keeping our operational expenses low and flat, thanks to our local-first route optimization engine working in the browser, and reliance on OpenStreetMap.

Well, trying out is better than a thousands words

Let's start it with index of whole Spain, 2.4gb download, 4gb on disk: https://gist.github.com/dkourilov/e243270684b5973f1fac005c78...

I'd say it's pretty usable to run a EU-sized country or several US states on any commodity PC. For embedded devices, it really depends what is the device. On Raspberry PI it should be fine for batch geocoding, realtime (typeahead) will definitely be lagging.

Have you measured actual memory and disk requirements of a photon OpenSearch index vs your sqlite database?

Why not package photon?

Google Cloud Armor plus Load Balancer?

You can balance traffic to external networks or clouds with it too.

But you _can_ open a bank account remotely for a DE LLC. Both Wise and Mercury supported this for years.

Even though Algorave is quite new, everyone who ever touched .mod/.s3m/.xm/.it can fell young again haha.

DJ_Dave live events are the best illustration for all of it. If you love electronic music, ever touched any generative art, and know basic coding this is for you.

Routing24 | Last Mile Logistics Expert | Remote (Worldwide) | https://routing24.com | Part-Time

Routing24 builds and provides professional route optimization tools to SMBs for free.

We are seeking a part-time consultant and advisor with extensive experience deploying commercial route optimization and TMS/DMS products in real-world business environments.

We offer hourly or per-project rates. To apply, please email: [email protected]

I'm still working on Routing24 https://routing24.com - free route optimization and planning app without stops or vehicles limit.

It's been 6 month since our first appearance on Show HN [1], and I'm working with first free users on bugs, improved workflows and UX, geocoding, solver features, future mobile app etc. etc.

We officially crossed the limits of 1500 stops per optimization with some waste collection guys, all still running fully client-side in the browser.

[1] https://news.ycombinator.com/item?id=41995427