Kalpit Champanery

🚀 building @HealthKey_HK | Ex. Staff Engineer @ottimate_ap(aka Plate IQ) | @91mobiles | @pricebaba | Co-Founder at Digital Web Weaver | coder | enthusiast

[Kalpit Champanery @ckalpit]

@0xSero @ivanfioravanti What about 48gb mx max?

[Kalpit Champanery @ckalpit]

@ivanfioravanti I was experimenting with this same setup on my m4 max and it is incredible. Although at some point I did thought that claude code is beemttwr but this is definitely better than what we we're doing 6 months back.

[Kalpit Champanery @ckalpit]

@opencode How it can or be HIPPA compliant? I want it to not store any of the api calls @opencode

[Josh Sabol @JoshSabol]

15:45 Clinical Trials conversation is 🎯

#1 challenge with running trials is finding qualified patients.

@HealthKey_HK, we actually ran the Lp(a) study Dave @EliLillyandCo discussed at 16:35. We processed 10,000s of patients, and found 216 qualified patients from a single clinic in <24 hours.

This technology was impossible to build until last year, and we solved it.

[Josh Sabol @JoshSabol]

Two big milestones today:

1. First customer that closed in under 24 hours

2. Three new customers signed (in one day)

LFG 🔥🔥🔥

[Kalpit Champanery @ckalpit]

@joedevon I also got excited with all the update. I'm yet to try checkpoint, resume and new context manager

[Kalpit Champanery @ckalpit]

I also have seen this for the first time!

seems like a recent change (and me not leveraging claude so much in my past couple of days)

[Kalpit Champanery @ckalpit]

TIL that when you do "/context" in CC, it fills up your context window by at least 1k tokens, not sure if its just me bcz of my claude_md file or its just the output of the /context that fills up the context window but in either case its better to use statusline functionality

[Kalpit Champanery @ckalpit]

I'll have to see that mobile one, to run it on my fold 6

[Sam Altman @sama]

gpt-oss is out!

we made an open model that performs at the level of o4-mini and runs on a high-end laptop (WTF!!)

(and a smaller one that runs on a phone).

super proud of the team; big triumph of technology.

[Kalpit Champanery @ckalpit]

@coderabbi Yeah is great. I was taking more in terms of when you want to use LLMs to return you structured output you night want to use with json or xml format prompt that has the output schema.

[Kalpit Champanery @ckalpit]

@evincc_ Ive seen it, seems like too much... have you used it?

[Kalpit Champanery @ckalpit]

Has anyone successfully built a claude code system where at the end of each session it can store the summary of the session and todos and then at the beginning of each session it can read last session's summary
I am trying to build one

[Kalpit Champanery @ckalpit]

Hey @AnthropicAI, I don't know how going from version 1.0.45 to version 1.0.44 is considered "Update" !
@claude_code

[Kalpit Champanery @ckalpit]

😮‍💨😞😣
Sad to see this happened to @AldebaranR

https://t.co/ZUwnp55FfR

[Kalpit Champanery @ckalpit]

@RaghavKhamar What do you mean by knowledge agents?

[Kalpit Champanery @ckalpit]

I see a lot of chatter about MCP being the next big thing, but I am not really sold on it yet!

[Kalpit Champanery @ckalpit]

@RaghavKhamar I saw a bunch of videos and all they were showing is github mcp and browser use, and I don't find it that much useful tbh