logged4upvoting

I would also add that having this kind of detection superpower probably requires the observer to be a social media addict too (low-key).

(This applies to Sol but probably works for Astra too)

I've created with Sol a skill called Low Quota Mode that intends to reduce the use of tokens usages by the frontier (intelligent model) and delegate the use of bulk reading of docs/code and implementation to a sub-agent running Luna Max. Sol is asked to supervise, read the diffs and approves the commit/pr.

The skill might need some iterations while you use it, for example at the end of a rough session you can ask Sol how did it went, which were the points of conflict with Luna and try to iron them little by little by editing the skill.

Also in difficult tasks, ask to babysit the sub-agent model, I've seen it makes more effort into communication between frontier and sub-agent to guide the task with more care.

So far it has reduced my tokens usage a lot (have not quantified but the quota lasts more).

I do "take pride" in things I put my time and thinking into, regardless of whether it is assisted or not. For example, I am somehow proud and like some songs that I produced using Suno because of the days I spent iterating on them.

Also in vibed projects that I put my time on. It is also true that it's been a long time without going back to a class or system I coded by hand just to "admire it" and get that feeling of, "omg, this class is fire!"

I see e2e encryption over photo galleries a must since is a way of protecting yourself against misconfigured servers, future exploits or unpatched software.

Shameless plug, I submitted a similar thought in here the other day. https://news.ycombinator.com/item?id=48503555

I like your approach of pooling resources around specific issues. That seems a practical missing piece for aiding the maintainers.

For me it is more like, i should have started leaving a trace before the invention of modern genAI, now maybe is late. I could have had a trusted trace to prove that I am a genuine human, now I get the impression that faceless new accounts/profiles or whatever are all fake and automatically managed.

I agree, and i think one more thing should be also explicit; save files.

Whether the game works offline, and until when the servers are guaranteed, is one part. But the savegames and progression data should also belong to the user.

The game is made by the studio, sure, but the save file is the part I construct by playing. It is my time, my choices, my progress, my world state and my memories.

So I would add a clear principle that the publisher should not be able to kidnap the user's save data.

So if i understand correctly is like

Application 1 has a Ed25519 keypair

Secret key private 3085c7405a88a968133e813e9f638a7d9b2e8088fe717ca535cc24d90b59815d

EndpointID or public key, for connecting to you: 274d4c656f064d4c59fffe7db38d6bf90d63cb087d0b2afd2cfa534334f7071c

and for connecting to App 2 you need to know the other endpoint id, no friendly "dnsish" name involved.

That is not true, over an extended task that you cannot keep complete in memory humans do not behave with 100% consistency.

I have labeled datasets with a human team and shown the same task to the same user on a different day, and they answered differently. Of course, they are usually consistent with themselves most of the time but not always.

What it would be interesting is a photo service back-end that can completely run with encrypted files in the server, like iCloud with Advance Data Protection.

All the processing is done on-device (phone) and the server is just for distribution