Sriram

3 years! One of my best decisions ever.

@eltigreindo largely nothing :) Wrote about it here - tsriram.in/blog/sabbatica…

@tsriram what did you do in those 6 months?

3 years! One of my best decisions ever.

@adipatil Absolutely! Would love to catch up. Ping me when you're here :)

@tsriram 👏👏 Will be in Chennai next month! Would love to connect in person and learn more!

Tell me you are in SF without telling me telling me.

@kevinwhinnery Congrats Kevin!

today, the @StainlessAPI team is joining @AnthropicAI ! we're bringing together experts in SDKs, CLIs, and MCP servers with the creators of MCP to make agents built on the Claude Platform even more connected & powerful. anthropic.com/news/anthropic…

Anthropic and OpenAI just became consulting companies. The crazy takeaway is they will make way more margin off their humans than their AI.

They grow up so fast! (talking about context windows)

@swyx Wooo 🥳

AIE coming to India soon!

Yay

I strongly believe there are entire companies right now under heavy AI psychosis and its impossible to have rational conversations about it with them. I can't name any specific people because they include personal friends I deeply respect, but I worry about how this plays out. I lived through the great MTBF vs MTTR (mean-time-between-failure vs. mean-time-to-recovery) reckoning of infrastructure during the transition to cloud and cloud automation. All those arguments are rearing their ugly heads again but now its... the whole software development industry (maybe the whole world, really). It's frightening, because the psychosis folks operate under an almost absolute "MTTR is all you need" mentality: "its fine to ship bugs because the agents will fix them so quickly and at a scale humans can't do!" We learned in infrastructure that MTTR is great but you can't yeet resilient systems entirely. The main issue is I don't even know how to bring this up to people I know personally, because bringing this topic up leads to immediately dismissals like "no no, it has full test coverage" or "bug reports are going down" or something, which just don't paint the whole picture. We already learned this lesson once in infrastructure: you can automate yourself into a very resilient catastrophe machine. Systems can appear healthy by local metrics while globally becoming incomprehensible. Bug reports can go down while latent risk explodes. Test coverage can rise while semantic understanding falls. Changes happens so fast that nobody notices the underlying architecture decaying. I worry.

average founder emotional arc

@jxnlco Where's the article? 👀

anyone have a podcast or want a lighting lesson about codex? I just wrote my codex maxxing article and want to try to give a live version of this

While everyone chases the latest AI tools, here’s an underrated, high leverage, practical application of AI: Give AI deep ongoing context on your product. Then actually use it during product discussions to keep you honest and call out your BS. AI is extremely good at this today.

Been using @sveltejs for a few projects lately, it's quite a nice alternative to React, fewer gotchas and complexity and Codex handles it really well. svelte.dev

Make every token count!

5. Hard budget caps that actually halt. Not the AWS "we noticed you spent $47K yesterday, here's a CloudWatch email" approach. Fail closed at the boundary. A Lambda stuck in a loop racking up data transfer or inference charges is a real failure mode; treat it as one!

Built a personal AI agent - why I did that and what it means. go.gov.sg/aiesingapore

POV : USING CLAUDE OPUS 4.7 TO JUST RENAME A VARIABLE

In the age of AI, the reader struggles because the writer doesn't have to.