Hacker News

Subscribe to Hacker News feed
Hacker News RSS
Updated: 53 min 18 sec ago

HMD Fusion easy to repair smartphone

Sun, 07/19/2026 - 4:19pm
Categories: Hacker News

Show HN: A schema you change by talking to it, without the model writing SQL

Sun, 07/19/2026 - 4:18pm

Wanted to try something new, decided to create a mutable crm, which re renders the UI after you apply a change. The llm only modifies the db via tool use, so he doesnt directly write sql, only choose which function to use and the params. Can only revert the last change, and dropping tables is not available to the llm. Looking for feedback, opinions, something you would do different. Taking my first steps in AI implementations. Heavily assisted by claude code

Comments URL: https://news.ycombinator.com/item?id=48971358

Points: 2

# Comments: 0

Categories: Hacker News

Prime Flow Field Background Animation

Sun, 07/19/2026 - 4:15pm
Categories: Hacker News

Is someone Into process mining? Let's talk in this thread

Sun, 07/19/2026 - 4:12pm

if you have solid insights on AI usage in industrial process mining this is the right place to start.

Comments URL: https://news.ycombinator.com/item?id=48971319

Points: 1

# Comments: 0

Categories: Hacker News

Pyinfra Is Underrated

Sun, 07/19/2026 - 3:54pm

Article URL: https://pyinfra.com

Comments URL: https://news.ycombinator.com/item?id=48971197

Points: 4

# Comments: 0

Categories: Hacker News

On Claude's Clotted Writing Style

Sun, 07/19/2026 - 3:48pm
Categories: Hacker News

Wigolo: Local first web search agent

Sun, 07/19/2026 - 3:42pm

Article URL: https://knockoutez.github.io/wigolo/

Comments URL: https://news.ycombinator.com/item?id=48971110

Points: 2

# Comments: 0

Categories: Hacker News

Show HN: BlazeRules – YAML rule engine for streaming data, 3M records/SEC

Sun, 07/19/2026 - 3:34pm

https://blazerules.dev I initially wanted to make a sub-millisecond log parser in C++ but that blew into a embeddable decision engine, that can run YAML defined rules on incoming data.

The rules are executed in a vectorized format on incoming data by reprojecting into a columnar format first, if it's not already. Depending on the payload size and rules complexity, the performance goes from 200K records/s to more than million records/sec, in terms of througput this would be around 200 MiB/s to 3 GiB/s on average.

Rules can be sql expressions too, or onnx models (numeric), window ops and quite a few more operations are supported.

It's comparable to DuckDB but for streaming data and on the fly decisions.

Comments URL: https://news.ycombinator.com/item?id=48971043

Points: 3

# Comments: 0

Categories: Hacker News

Show HN: Chalie – AI peer not employee

Sun, 07/19/2026 - 3:34pm

Article URL: https://github.com/chalie-ai/chalie

Comments URL: https://news.ycombinator.com/item?id=48971042

Points: 3

# Comments: 1

Categories: Hacker News

Pages