There’s only one way to implement a mission, an algorithm, a task. But there’s an infinity of path, inconsistants, fuzzy and always subjective way to live. Thàt’s our lives, that’s the code LLM are trained on. I do not think, and hope, it will ever change much

Hi gemini, i’ve booked some tickets for théater. Please look into mail mailbox, schedule it in my calendar and confirm me the planning for next week.

Beeing able to use natural processing my mail and calendar make me switch to gemini (app), there’s no way to achieve that with chatgpt (app)

Gemini is now good enough, even if i prefer chatgpt.

I only care about what i can do in the app as paying customer, even if, aside from that, i am working in IT with the SDK openrouter & MCP intégration & whatever RAG & stuff for work

They are trained with 100% true facts and sucessfull paths.

We humans grec our analysis/reasoning skills towards the 99.9999% failed attempts of everything we did, uncessfull trials and errors, wastefull times and frustrations.

So we know that behind a truth, there’s a bigger world of fantasy.

For LLM, everything is just a fantasy. Everything is as much true as it’s opposite. It will need a lot more than the truth to build intelligence, it will require controled malice and deceptions

I was with you until the very last line, can you expand on that?

I think he was getting at the fact that the Truth is not good news to everyone.

It’s a great time to start a CD burner business — I foresee public market demand soon

Using continious letters for addititives values is a good idea (F+3) can be predicted easily. Yet i agree that confusing « symbols » should be avoided. Forcing UPPERCASE formeront plus using a prefix (Z might be a good one)

ZA:03 ZB:23 ZL:55 ZI:12 ZO:08

would work greatly for me

Z can look like 2 in sloppy handwriting.

If OpenAI offers Codex and Anthropic offers Claude Code, is there a CLI integration that Google recommends for using Gemini 2.5? That’s what’s keeping me, for now, with the other two.

Claiming impostor syndrome is very different from having a crisis of confidence.

Is there a specific reason to make a distinction between the two products (copilot/chatgpt+) when in the end, they are using the same engine.. ?

It is confusing me a bit (chatgpt+ subscriber here)

Plenty of custom system prompts for co-pilot probably.

A french classic (but less impressive) Si mon tonton tond ton tonton, ton tonton sera tondu.

(If my uncle shave your uncle, your uncle will be shaved)

And for deutsch/german

Nach dem stutzen des Rhabarberbarbarabarbarbarenbarts geht der Rhabarberbarbarabarbarbarenbartbarbier meist mit den Rhabarberbarbarabarbarbaren in die Rhabarberbarbarabarbarbarenbartbarbierbierbar zu Rhabarberbarbarabarbarbarenbartbarbierbierbarbärbel um sie mit zur Rhabarberbarbarabar zu nehmen um mit etwas Rhabarberbarbarabarbarbarenbartbarbierbier von Rhabarberbarbaras herrlichem Rhabarberkuchen zu essen.

https://www.oezeps.at/wp-content/uploads/2011/10/Rabarberbar...

what makes you think docker swarm is abandonned ? The latest docker engine release (23.0) continue support it and add new features

A few years ago (2018?), I read somewhere - I think it was on Hacker News, even - that Docker/Moby was quietly dropping paid support for Swarm.

I've had a hard time finding much via hn.algolia.com to back this up, other than some discussions in mid-2018, though.