edf13

Joined 9 years ago

Karma
1,514
Submissions
683
Member since
Oct 20
hello at fieldlogic.uk
View on Hacker News

Recent submissions

Comment · 9 days ago
> Kaushik holds a Bachelor's in Computer Engineering (member of Tau Beta Pi) and a Master's in Computer Engineering with a focus on Networking

First one I clicked on?

Comment · 22 days ago
This is the real headline... and more so that it has been hidden away.
Comment · 1 month ago
A few of us old boys can still maintain Cobol
Comment · 1 month ago
You also need to compare allowances on Codex vs. Claude Code
Comment · 1 month ago
Recent PR I had to review...

PR content:

``` Lots of AI slop.... .... .... Note: this will not build due to XYZ .... .... More AI slop .... .... End of PR ```

So the dev hadn't even read the PR comment himself and had blindly posted it!

Comment · 1 month ago
It is AI gen - and it's not so much of a project, more of a quick tool/status bar.
Comment · 1 month ago
Yes - we hook into that to add the cost/turn and the burn rate
Comment · 1 month ago
I kept running into limits on my Claude Code sessions (Especially with leading edge models)... the main cause being session hygiene, not clearing or compacting my sessions often enough.

So I built this simple tool to show my current session status.

Comment · 1 month ago
Hi,

I'm Dan and I staarted building grith AI earlier this year after getting annoyed with constant permission prompts from Claude Code and Codex.

I had previously built an email security service which relied on a pipeline of multiple filters, each one building up a score of an incoming message - allowing the system to auto approve or deny an message in almost all cases and if it was unsure it would add it to an email digest/report letting the user choose to allow or block.

This process is the basis for grith - we currently have 18 filters and 1617 patterns which build a score for every action a agent takes - everything <= 3.0 is automaticialy approved, everything > 8.0 is automatically blocked... the ones inbetween we prompt the user.

What this means in practice is that the user sees very little prompts - in a records 120 claude code session a user only ever had to respond to 0.27% of prompts... not 40 or so an hour you'd see in normal use and not the dangerously blind approval --dangerously-skip-permissions or auto mode would give you!

Grith is free with no account needed, no phone-home and open source. Paid tiers bring teams, online dashboards, centralised policies, verificable analytics and more.

Linux first with Windows and Mac launching soon.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton