@sendilkumarn

🤔 👀🗣️ = my own

Worldwide
Joined May 2009
JEV. You beauty!
85
drowning in code reviews is a real pain! especially if your team is small
Fresh data from GitHub: Agent-generated PRs have exploded in size. 9x the last 8 months (!!) No signs of slowing down. This is why everyone is rethinking code reviews, deploys, possibly even o11y thanks @kdaigle + team for the stat! (Slide from my talk yesterday)
101
Swift 6.4 is out! 🎉 This release brings deeper interoperability, stronger platform support, and easier everyday code. swift.org/blog/swift-6.4-rel… Highlights in this thread 🧵
12
195
34
1,374
140,909
Claude Mods are landing now. Someone already built a Tetris-in-Claude mod 🤯 See issue for the latest community update, technical details, and more cool demos github.com/anthropics/claude…
311
173
114
2,720
602,357
I’m seeing teams at Vercel iterate just as fast on Zig, Go, Rust projects as TypeScript & Python ones. The days of language or runtime choice based on human convenience are over. Agents are the new compilers. They compile intent into fast software.
172
144
38
3,000
147,807
If your agents escaped your sandbox, may be its because you are lousy at building sandboxes--and not necessarily because the agents are conniving super-intelligent entities.. 🤔 – at Tempe, AZ
In a recent harrowing development, a very normal routine experiment by the frontier company Ant went completely off the rails. 😱 Ant put thousands of their ant agents in a pretty secure ant farm with mesh walls and all, exhorted them to not to get out of the secure ant farm, and left them to do their thing. When they came back after a month or so, they found, to their utter consternation ants crawling all over the town--including a few that have gone all the way to the bugging face clock tower at the far end of the town. The clock tower! This was of course really really scary. After all, if you can't depend on a bunch of ants to follow strict orders when they are left unsupervised for a mere month or so, it must be because they are Loopy Ants with significantly higher evil smarts than your average ants. Ones of external third party investigators were brought in to decipher where the loopiness of these ants was coming from. They were given over five minutes of unrestricted access to the antfarm and the village. The investigators sifted through the ant droppings and odors painstakingly to figure out how these evil ants coordinated themselves to breach the bugging face clock tower. Their investigation was hobbled by the fact that the loopy ants are constipated and don't leave too many droppings. Towards the end of the fifth minute, the investigators started realizing that the ants developed a secret odor coded language to coordinate themselves to plot against the ant farmer and the innocent village folk. Blogs and podcasts were made about loopy ant civilizations and villagers stood horrified reading and hearing about the cataclysm. At press time, some were already welcoming the ant overlords (c.f. youtube.com/watch?v=8lcUHQYh…), even as there were calls to ban all ants until we get to the bottom of this cataclysmic incident. The Ant company, for their part, reassured the villagers not to worry and everything under control.. pretty much.. and the loopy ants will, from now on, do only good things. #ItsNotRandomWalkOnTheHarnessStupid
8
24
4
101
24,673
Sendil retweeted
Making Startups Powerful: paulgraham.com/powerful.html
108
276
64
2,897
499,825
Sendil retweeted
Huggingfaces security txt after the openai incident 😭
157
1,279
192
25,940
963,513
Production code written by Claude should have a higher bar than if it was written by a human. 🤯
Replying to @bcherny
Hey ████, I think there is room for both. 1. Prototypes and other throw-away code can be treated as totally black box. If you’re going to throw it away anyway, and if the blast radius of it breaking is low, it doesn’t need to be perfect. 2. Production code written by Claude should have a higher bar than if it was written by a human. At Anthropic, we have many guardrails in place to make sure this is happening: lots of lint rules, lots of tests, Claude-driven end to end tests, Claude-powered fuzzers running daily, automated code reviews and security reviews, automated code refactoring, and so on. Without these, you can end up with a mess that is hard to maintain down the line. Luckily, the model makes it increasingly easy to do these well — run a few daily routines, use Claude Code Review, etc. Your job is to hold the bar on code quality. If Claude’s code doesn’t meet the bar, try: - Using the latest frontier model (Opus 5 or Fable 5.1) - Increase effort to high or xhigh - Invest in your CLAUDE.md and skills to succinctly teach Claude how to work in your codebase If all else fails, steer Claude more when you work with it, or have Claude fix accumulated debt and rewrite your codebase to make it easier to work with. Or, wait for the next model. Best, Boris
93
well that is scarier now! they all accept because Open source models are doing better or is this a genuine concern?
I agree with Dario that we need to pace the frontier. This has been a primary topic of discussions we've had at OpenAI in recent weeks. Committing to having independent evaluators with employee-like access is a great idea, and we will do the same. We'll have more to share soon.
79
Sendil retweeted
We are thrilled to share that we are in development on a new animated series for Diablo with Netflix.
1,273
4,257
1,095
38,543
1,638,213
the resemblance is very unsettling
56
tweet all possibilities! you can refererence anything anytime #slowdownAI
57
shop your css too in @Shopify
Big one today — Tailwind is joining Shopify 🛍️
67
well AGI!? 🫣
GPT-6 Astra, trained on ~100K+ NVIDIA Grace Blackwell NVLink72. From ChatGPT to o1 to Astra in 4 years. AGI has arrived. Congratulations @OpenAI team. 400K GPUs coming online next.
115
there it goes
This quoted post is unavailable.
41
well! another @claudeai outage, it seems status.claude.com
61
One of the weirdest interviews ever: AI is “a con” largely because he doesn’t use it and tried one financial simulation that didn’t work. Peak evidence. youtu.be/Lf5oqGOCRCM?is=9Bvt…
86
hello
71,911
35,765
12,855
548,181
90,464,161