Hacker News: edf13

New comment by edf13 in "eMudhra to exit global SSL/TLS certificate business"

edf13 — Thu, 22 Oct 2026 14:37:36 +0000

> 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?

New comment by edf13 in "Cloudflare acquires Deno"

edf13 — Fri, 09 Oct 2026 13:36:45 +0000

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

New comment by edf13 in "Claude partial outage"

edf13 — Tue, 29 Sep 2026 15:05:54 +0000

A few of us old boys can still maintain Cobol

New comment by edf13 in "GPT-6 Sol and Luna"

edf13 — Tue, 22 Sep 2026 18:20:11 +0000

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

New comment by edf13 in "If coding is solved, what now?: Measuring the sloppiness of code"

edf13 — Fri, 11 Sep 2026 15:42:15 +0000

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!

New comment by edf13 in "Show HN: ClaudeStatsBar: your session is 486k deep and nothing told you"

edf13 — Fri, 11 Sep 2026 14:30:22 +0000

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

New comment by edf13 in "Show HN: ClaudeStatsBar: your session is 486k deep and nothing told you"

edf13 — Fri, 11 Sep 2026 14:06:52 +0000

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

New comment by edf13 in "Show HN: ClaudeStatsBar: your session is 486k deep and nothing told you"

edf13 — Fri, 11 Sep 2026 13:45:43 +0000

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.

Show HN: ClaudeStatsBar: your session is 486k deep and nothing told you

edf13 — Fri, 11 Sep 2026 13:43:53 +0000

Article URL: https://github.com/Field-Logic-Ltd/ClaudeStatsBar

Comments URL: https://news.ycombinator.com/item?id=49658328

Points: 18

# Comments: 15

A Git Config Key Ran Code in Seven Coding Agents. The 2022 Fix Does Not Stop It

edf13 — Wed, 09 Sep 2026 14:53:17 +0000

Article URL: https://grith.ai/blog/git-config-key-2022-fix-coding-agents

Comments URL: https://news.ycombinator.com/item?id=49627616

Points: 4

# Comments: 0

New comment by edf13 in "Show HN: Grith – syscall-level supervision for AI agents"

edf13 — Tue, 08 Sep 2026 13:22:42 +0000

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.

Show HN: Grith – syscall-level supervision for AI agents

edf13 — Tue, 08 Sep 2026 13:22:25 +0000

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

Comments URL: https://news.ycombinator.com/item?id=49610006

Points: 3

# Comments: 1

New comment by edf13 in "216M Spy TVs – The LG Smart TV Problem [video]"

edf13 — Mon, 07 Sep 2026 12:41:07 +0000

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>

New comment by edf13 in "Ask HN: How do you manage skills files?"

edf13 — Mon, 07 Sep 2026 12:12:32 +0000

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.