@TablePlus Why no tab autocomplete ai?
I canβt tell you the number of times I write queries in cursor and copy them to TablePlus because itβs 100x faster with tab autocomplete
You might believe you should spend less time thinking about code because of AI.
I strongly disagree! Weβre watching this play out live where tons of AI generated code becomes a liability.
At the end of the day, an engineer needs to be responsible / on call for code that gets shipped to production. If you donβt understand the system youβre trying to debug, youβre probably going to have a bad time.
Yes, AI can help with all of this, if you set up the proper systems. You can have agents triage prod logs, look at errors, etc. You can speed up parts of the investigation, but an engineer needs to make the call. There might be serious customer or financial implications from that change.
I expect the trend continue for trimming dependencies, vendoring code so you can modify it directly, preferring simpler systems with fewer abstractions, and spending waaaay more time thinking about system design and code maintenance.
Iβve said this before, but itβs a great time to get familiar with CS fundamentals and some of the history behind what great software looks like. Many parts will be different in the coming years as AI progresses, but also a lot more than people realize will stay the same.
@adamdotdev@threepointone I thought being able to code from away from my computer was the best thing ever and it turned out to be a terrible idea. I was never present.
I made it a point to myself never to prompt coding agents away from my computer, theres a time and place for work.
Cursor is making a platform play. Right now they're an IDE. By releasing the SDK, they're turning their agent runtime into programmable infrastructure that runs headlessly in CI/CD pipelines, internal tools, and even third-party products. Every agent spun up through the SDK burns tokens on Cursor's billing. That means revenue scales with compute, not seats, and without a human in the loop, volume can go way higher. Smart move!
@jpschroeder@zeeg The amount of noise in sentry is insane. Feels like 80% of the errors we get are transient errors nothing to do with our code or platform
Race to the bottom, inference for the same level of work goes down over time.
Insane token prices Γ la opus, will be hard to justify and will likely be reserved for very specific tasks like running security audits, where you absolutely need SoTA.
dear god lol - new kimi model is a fucking beast.
GPT 5.4 level coding, 76% cheaper than opus 4.7 and 100% open source / free to use, i mean look at this:
> kimi k2.6 can code continuously for 12 hours straight, run 300+ agents in parallel from a SINGLE prompt.
how the fuck is china doing this?
every 3 months theres a new open model that gets closer to the best claude/GPT models.
deepseek also releasing this week.
open source models have caught up and china of all countries are leading it!
Hey, I'm open-sourcing Clicky.
Go forth into the wild and build the future of education and the future of AI interfaces, my friends. I'm happy to have given a spark.
Enjoy!
https://t.co/x1gR0dib1p
I built this thing called Clicky.
It's an AI teacher that lives as a buddy next to your cursor.
It can see your screen, talk to you, and even point at stuff, kinda like having a real teacher next to you.
I've been using it the past few days to learn Davinci Resolve, 10/10.
the guy keeps saying "you can already do this with a canvas behind the element" so here is another gratuitous animation where the scanline physically distorts the form content as it passes (warping the actual rendered HTML pixels)
Introducing render-json
The Generative JSON framework.
1. Point it at anything
2. It generates JSON
3. That's it
Apps, games, and more. If it exists, it can be converted into a JSON spec.
πππ π @ππππ-ππππππ/ππππππ-ππππ