Sandip Wane

@kitlangton Is this purely from replacing the existing functionality with Effect TS lib?

2 founders down. 1 to go.

lol, so cringe but so good. Love it

This is my favorite blog to share when someone asks how to write an Agent.

I’ve climbed my way from the left side of that curve to the right.

@rakyll Jaana kidhar hai?

Uber driver: Your name means Go. Me: I know 😎

Note to self :

seems obvious but: things that are changing rapidly: 1. context windows 2. intelligence / ability to reason within context 3. performance on any given benchmark 4. cost per token things that are not changing much: 1. humans 2. human behavior, preferences, affinities 3. tools, integrations, infrastructure 4. single core cpu performance therefore, ngmi: 1. "i found this method to cut 15% context" 2. "our method improves retrieval performance 10% by using hybrid search" 3. "our finetuned model is cheaper than opus at this benchmark" 4. "our harness does this better because we invented this multi agent system" 5. "we're building a memory system" 6. "context graphs" 7. "we trained an in house specialized rl model to improve task performance in X benchmark at Y% cost reduction" wagmi: 1. product/ui 3. customer acquisition 4. integrations 5. fast linting, ci, skills, feedback for agents 6. background agent infra to parallelize more work 7. speed up your agent verification loops 8. training your users, connecting to their systems and working with their data, meeting them where they are

@adamdotdev Try using opencode zen

Every time I hit my Claude quota

@Madisonkanna @thdxr At this point I’m not sure if this is actually @thdxr and honestly I’m afraid to ask

At Dax’s in Miami about to record a conversation! What questions do you have for @thdxr?

@mati_matiiiiii @steipete @RunBanco Wonder what this dude must be thinking…

Burrito time with @steipete @RunBanco

@chribjel @thdxr @thsottiaux +1

@thdxr @thsottiaux Could be an opt-in though. In the opencode.json or something. This way repo owners can know and decide if they want it

Do people like this? We don't do this for codex because it exists to help you and it's important that you remain the owner and accountable for your work without AI taking credit. At the same time it does mean that you can't trace how popular codex is among repos.

Peak AI Engineer

👋 Roughly, the more tokens you throw at a coding problem, the better the result is. We call this test time compute. One way to make the result even better is to use separate context windows. This is what makes subagents work, and also why one agent can cause bugs and another (using the same exact model!) can find them. In a way, it’s similar to engineers — if I cause a bug, my coworker reviewing the code might find it more reliably than I can. In the limit, agents will probably write perfect bug-free code. Until we get there, multiple uncorrelated context windows tends to be a good approach.

@kianmckenn @kitlangton has a good metaphor it's like tending a garden can let ai code grow but you have to aggressively clean up after it and be diligent about architecture and patterns codebase is ok it will get better

🥹🤌🏻

It’s not about junior vs senior, it’s about “good with AI” vs “not good with AI.”

@trq212 Okay. So how many startups got killed by this??

Voice mode is rolling out now in Claude Code. It’s live for ~5% of users today, and will be ramping through the coming weeks. You'll see a note on the welcome screen once you have access. /voice to toggle it on!

@thdxr 👍

@mitchellh Hashi-bhai approves ✅

I know this is pretty well established at this point, but Codex 5.3 is a much more effective model than Opus 4.6. I went back and forth on both for a bit, but haven’t touched Opus at all now for a full week. First model to get me off of Opus… ever. Good job Codex team.