indranil ganguly

MLE • AI • love building games

[Addy Osmani @addyosmani]

https://t.co/HUnW9a2buA

[Addy Osmani @addyosmani]

Before adding another subagent ask what problem it's solving. A bloated system prompt is often the issue.

Skills and tool search can fix that without splitting context across agents. My rule of thumb is to keep a subagent when the work is parallel, needs fresh context or one agent really can't pick the right tools.

Otherwise, fold it into the main loop, turn its prompt into a skill, run your evals and keep whatever wins.

Good write-up:
https://t.co/1gcrNNpQru

[indranil ganguly @Indranil_bonty]

@omnirushai @ClaudeDevs @claudeai @bcherny @lydiahallie Just deepwiki no other MCPs. Though i was running it at xhigh but it was working fine earlier.

[indranil ganguly @Indranil_bonty]

My claude usage limit is draining so fast from last 3 days it feels that the usage limit doesn't even exist.
Can anyone of you please help.
@ClaudeDevs @claudeai @bcherny @lydiahallie

[indranil ganguly @Indranil_bonty]

@ManUtd How can this team even play at UCL. Its high time for introspection, making money through merchandise wont last long. This team is a sinking ship now.

[Hamel Husain @HamelHusain]

New blog post 🎉: How To Use Decision Models For Evals

In this post, we show you how to choose a decision model for your task, tune its threshold (don't assume the 0.5 default is good!), and interpret its scores.

Lots of cool interactive charts here. https://t.co/uYAfte9Kb5

[Dipanshu Kushwaha @Dipanshu_AI]

00:15 - The right way to prompt Claude
33:21—What makes Claude act dumber in your code
01:33:39 - How Anthropic uses Claude every day
02:50:56 - A fix that makes Claude way smarter - This

The 4-hour Anthropic free course replaces about 10 paid engineering courses.

Watch it today, then bookmark it for later.

[indranil ganguly @Indranil_bonty]

@thsottiaux @thsottiaux sol 6.1 is consuming tokens way faster these days. That wasn't the case earlier

[Hugging Face @huggingface]

Learn about how to get multipliers in local LLM speed-ups using speculative decoding in this livestream with @mervenoyann, @MaartenGr and @_EldarKurtic

https://t.co/tFexgaLcT5

[Niels Rogge @NielsRogge]

How to do this?

Simply point Claude (or another coding agent) to https://t.co/3qMnWbpe1e and ask to run it with llama cpp.

Then, open llama’s web UI and start chatting!

[merve @mervenoyann]

actually if you want to get started here this is a bit advanced. I have a PR to llama.cpp docs which illustrates better from scratch, please check this out instead https://t.co/38OBgTPevm

if you want to understand why spec dec is needed, check this primer on generation out https://t.co/38e5I2wU4y

[indranil ganguly @Indranil_bonty]

@NielsRogge @NielsRogge can you tell me little about your setup. What connectors do you use in claude desktop

[leonie @helloiamleonie]

how do you fine-tune a decision model on your own data?

in these two notebooks, you'll learn:
• how to prepare the training data
• how to fine-tune our d1-3B decision model
• using @UnslothAI and @huggingface TRL

all within 30 minutes on a free-tier GPU.

unsloth: https://t.co/VxwfzlwHXP

TRL: https://t.co/yqzvFwVoZ5

ps: how adorable are these halloween kitties? 👻

[Josh Rosen @JoshARosen]

https://t.co/N1cpmx12SY

[indranil ganguly @Indranil_bonty]

@NielsRogge I thought you don't use claude anymore ?

[indranil ganguly @Indranil_bonty]

ChatGPTs intelligent UI is sooo impressive.
@thsottiaux 🔥🔥

[Cindy Sridharan @copyconstruct]

How to effectively debug with agents when you no longer read or understand the code

In this post, I propose a debugging framework for agents that doesn’t rely on human knowledge of code to get to the right “root cause”

The TL;DR are the screenshots.

Link to post in the reply.

[Hugging Models @HuggingModels]

This is a goldmine, bookmark worthy.

[indranil ganguly @Indranil_bonty]

@mervenoyann I really learn so much from you awesome guys 🙏. Hopefully someday i can also share some interesting stuff 🤞

[Sebastian Raschka @rasbt]

Took a while, but here it is, a mega write-up on language models for text classification and, of course, Jev.

It's basically a visual guide to RNNs, CNNs, transformers, and calibration, with hands-on experiments on accuracy and efficiency.