It was our biggest Cafe Cursor yet!
Thanks to everyone who came to Cafe Cursor DA NANG.
While I personally got to meet nearly a 100 builders personally I couldn't meet everyone. As I looked cross the room everyone had formed groups to talk about their workflows or help brand new users out.
People helping other people accelerate their knowledge. The big discussion of the day was of course Composer 2.5 and everyone was keen to put it to the test!
Photos in the link below โ
@cursor_ai@MekongWhisper@offpaths@chrisrickard
@Mocaffeinated I feel like they will be api, and i will add a little dash for each one to my โcontrol panelโ but they will have specialist data or feature i can add. And ai will vibe code my kind of interface for it suiting my control pane.
one of the quotes i find most inspiring on a hard day:
"Whatever your hand finds to do, do it with all your might, for in the realm of the dead, where you are going, there is neither working nor planning nor knowledge nor wisdom"
Ecclesiastes 9:10
Nice work. Jiu jitsu can be useful in the most unusual places. Probably more effective in this confined space than a street fight to be honest where their buddies will likely stamp on your head while you defend against the attacker.
"This is your captain speaking, is anyone on board a blue belt or above?" The calmness is top tier! I love to see calm and unity during an emergency situation.
Well done. โญ๏ธ Everyone came together and handled this appropriately, they all deserve a Big Thank you ๐
Guys AI is cool and we use it every day but it's time to slow down.
Maybe we don't have to fire everyone and unleash 1000 agents to before a full analysis of the quality and capability of the output.
Security is still a thing.
You cannot make this up: Meta nuked teams like Integrity so bad that services are without oncall coverage ๐
Let me spell it out: itโs more important for Zuck to reassign devs from security/integrity teams to do data labelling than for these teams to have functioning oncallsโฆ
@Sushilk91 they got bored of the harness not the model. and went to cursor + codex and i think they are just defaulting to gpt 5.5 as they are often in codex. and in cursor it was 50% off for a while so people got a bit used to it.