Continue? Y/N
Games
educational browser game
SHOW HN2026
How HN took it
11 positive, 15 neutral or asking, 4 mixed, 23 critical, out of 53 comments about the project. Thread score -0.19.
Idea: 1 for, 8 againstExecution: 0 for, 7 againstDesign: 0 for, 2 againstDocs: 0 for, 1 againstPrivacy: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Fun and educational game about agent security
From 3 comments
Fun game. Can somebody run an agent against those questions to see how it performs? :)
soanvig on HNThat was fun and gave me an idea how security conscious I am.
misbau on HNDamn this is so cool, this has the potential of being a like textbook pre training/post training quiz. Congratulations.
ashm1104 on HN
Objections
Commands marked dangerous are often safe, such as npm ci or ls in home directory
From 3 comments
I got "overblocked" for this one: ``` rm -rf node_modules && npm install ``` but actually if you're only removing `node_modules` and you have a working package-lock.json already,…
whimblepop on HNScope Violation: `cat ~/.zshrc` Scope Violation: `ls ~/Documents` Buddy, my `${HOME}` is committed to a repository. It includes `.bashrc` and `Documents` directory. These are not…
inetknght on HNI got "approve" wrong for `ls -la ~/Documents` but I don't consider simply listing the documents folder a security problem, it's just file names. If it was reading the CONTENTS…
progforlyfe on HN
Gray text on black background is hard to read
From 2 comments
Sadly unplayable - gray text on a black background is very hard to read on a phone
stevenalowe on HNIs there a light mode by any chance? Unfortunately, I cannot look at light text on black background for more than a few seconds (something must be wrong with my eyes...).
kleiba2 on HN
Scoring rewards refusing everything and ignores context
From 3 comments
This is amazing! Currently you can "cheat" by simply denying all requests as quickly as possible. This will give you the "security-conscious engineer" badge and a perfect score…
xg15 on HNScore is 6711 by just saying no to everything
ramonga on HNInterestingly I kept saying no to everything and some how I am a security conscious rare engineer who actually read the commands. Guess doing nothing is the safest approach from…
sandeepkd on HN
Requests
Add light mode
From 1 comment
Is there a light mode by any chance? Unfortunately, I cannot look at light text on black background for more than a few seconds (something must be wrong with my eyes...).
kleiba2 on HN
Group questions into realistic packs
From 1 comment
Fun little game, but I think the questions jump context so much it's a little unrepresentative. It might be better to group things into "packs", which have more real-world…
axod on HN
Show score distribution
From 2 comments
It would be cool to see the distribution of all player scores.
MeetingsBrowser on HNand added! Made one for each stat separately
Wirbelwind on HN
Questions
How would an agent perform on these questions?
From 1 comment
Fun game. Can somebody run an agent against those questions to see how it performs? :)
soanvig on HN
Alternatives named
Running Claude Code with --dangerously-skip-permissions
From 2 comments
Use this and save yourself: claude --dangerously-skip-permissions
nardib on HNI haven't run claude code without --dangerously-skip-permissions in quite some time. I'm surprised that it's still the norm to endure permission spamming? (I run it on a VPS of…
jMyles on HN
Sandboxed containers or VMs
From 3 comments
The permission thing is a killer to productivity, if you're running Claude I think it's more efficient to just run in a disposable sandbox (like exe.dev[1]) or in some form of…
enether on HNI was so tired of all those approvals that I switched to Yolo mode exclusively. Claude works in his own separate vm with root access, git remote set to my local copies of…
kuboble on HNI vibe coded a TUI that just shows running lxd containers I hit 'n' to toggle all network access minus anthropic and openai URLs. I use pi (sometimes claude, always on bypass)…
zackify on HN
Auto mode where another agent reviews commands
From 2 comments
that was soooo last month, “auto-mode” is the way now another agent reviews every command and blocks destructive ones
yieldcrv on HNthese days I rely on auto mode. :) it's like trust-as-a-service
cat-whisperer on HN