edf13

I’ve been looking into a smaller scale option to run limited items medium term on part time hours…

Best option so far involves a mix of batteries that are charged from the mains when available and topped up from a mix of solar and a LPG/multi-fuel generator.

But unless you want to go very large on the solar and generator size it’s unlikely to cover everything full time.

> 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?

This is the real headline... and more so that it has been hidden away.

A few of us old boys can still maintain Cobol

You also need to compare allowances on Codex vs. Claude Code

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!

It is AI gen - and it's not so much of a project, more of a quick tool/status bar.

Yes - we hook into that to add the cost/turn and the burn rate

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.

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.

Be interesting to know the true cost of smart TVs without the subsidized benefit of tracking that the "smart" element has.

A comparison of a dumb 4k panel vs the equivalent "smart" tv for example>

One thing to consider when you do look at how you manage your installed skills - is the security side of them.

You also need to manage the authority of each skill too. Signed skills is a step in the right direction, but it only proves provenance and doesn't prove behavior.

(Related: https://news.ycombinator.com/item?id=49597166)

Any video demo available - love to see it in action

Odd… UK visitor and I get:

Website Not Allowed “⁦‪prismml.com‬⁩” is a restricted website.

Exactly - the flow of AI assistance makes it so much easier to get caught in the one more feature trap!