Sandip Wane

AI Engineer | Building at @cloudhedgeio | Husband to @paw_lish

[Sandip Wane @sandipwayne]

@thdxr fair push back…

[Sandip Wane @sandipwayne]

@oguzydz @bcherny +1

[CinemaCopa @CopaExMachina]

"He turned the volume up because he can't hear the dialogue. Now make the action scenes as loud as possible."

[Sandip Wane @sandipwayne]

@gregpr07 Why did this make me laugh so hard

[Sandip Wane @sandipwayne]

@adamdotdev Adam, please do a new episode of “How about tomorrow” 🙏

[Kalbur Saman @kalbursamantr]

Nadir bulunan arabayı aldıktan bir dakika sonra;

[Sandip Wane @sandipwayne]

Claude is so cute it will try it's best to follow user prompt. lol

[Thariq @trq212]

https://t.co/MXt5XS4xBX

[Sandip Wane @sandipwayne]

LLMs are like gasoline. Harnesses are like cars.

Some built for speed, some for all-terrain, some for efficiency. Same fuel, wildly different machines, each tailored for specific job.

[Sandip Wane @sandipwayne]

Current agent harness design trend

> thin harness
> fat skills
> metadata first
> instructions second
> resources last

[Sandip Wane @sandipwayne]

> Great interfaces rarely come from a single thing. It's usually a collection of small details that compound into a great experience

https://t.co/R2ZWhYnsSQ

[Sandip Wane @sandipwayne]

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

[Sandip Wane @sandipwayne]

lol, so cringe but so good. Love it

[JNS @_devJNS]

Claude code so freaking good lately, someone dropped a banger on it 😂

[Sandip Wane @sandipwayne]

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

[Thorsten Ball @thorstenball]

A year ago we just said the emperor has no clothes.

https://t.co/vyksNX3br4

[Sandip Wane @sandipwayne]

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

[Josh @josh_bickett]

What is an AI agent?

[Sandip Wane @sandipwayne]

@rakyll Jaana kidhar hai?

[Sandip Wane @sandipwayne]

Note to self :

[Boris Cherny @bcherny]

Mistakes happen. As a team, the important thing is to recognize it’s never an individuals’s fault — it’s the process, the culture, or the infra.

In this case, there was a manual deploy step that should have been better automated. Our team has made a few improvements to the automation for next time, a couple more on the way.

[rahul @rahulgs]

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

[Sandip Wane @sandipwayne]

@adamdotdev Try using opencode zen

[Sandip Wane @sandipwayne]

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