Rohit Yadav @rohitdev_

Building AI-powered data systems. rohity.com Joined November 2022

Tweets

32
Followers

426
Following

95
Likes

7K

Rohit Yadav @rohitdev_

a month ago

Speed of writing code is no longer a bottleneck.

0 0 0 7 0

View Details

Lost an afternoon to what looked like an off-by-one. The loop was right. The input wasn't. np.arange(1, 1.3, 0.1) returns 4 elements, not 3. Float accumulation drifts the last value past stop. For evenly spaced floats, use np.linspace: specify the count, not the step.

0 0 0 14 0

View Details

Rohit Yadav @rohitdev_

a month ago

Stop making users do mental gymnastics in your data pipelines. I just renamed `is_not_historical_data` to `is_nrt`. Every read used to force a double-negation. Now the queries actually read like English.

0 0 0 20 0

View Details

Rohit Yadav @rohitdev_

2 months ago

Everything you say will be judged by an LLM.

0 0 0 20 0

View Details

Rohit Yadav @rohitdev_

2 months ago

rohity.com/blogs/why-you-…

0 0 0 19 0

View Details

Rohit Yadav @rohitdev_

2 months ago

Which Agent Harness do you suggest using with Grok?

Brian Roemmele @BrianRoemmele

2 months ago

Anyone telling you that you need to use Claude to run just about any OpenClaw spending a wacky $1000 or more per month is no expert you should trust. Use @Grok. Great pricing and 4.3 is in another category. You won’t be burning $1000 a month. You will absolutely thank me.

670 358 6K 40.2M 2K

0 0 0 29 0

View Details

Rohit Yadav @rohitdev_

2 months ago

Design is an act of creativity and LLM tools are not creative yet.

0 0 0 12 0

View Details

Rohit Yadav @rohitdev_

2 months ago

If you can think, you can build.

0 0 0 17 0

View Details

Rohit Yadav @rohitdev_

2 months ago

A new idea, if not moved forward quickly, wilts.

0 0 0 12 0

View Details

Rohit Yadav @rohitdev_

2 months ago

You’ll really start to notice these limitations when you’re building an AI Agent (interacting directly with a model API) or when you're running a local model. In those cases, you’re dealing with a pure text predictor, and that’s where the "math logic" can easily break down.

0 0 0 18 0

View Details

Rohit Yadav @rohitdev_

2 months ago

While apps like ChatGPT and Gemini now have built-in tools for searching the web or doing math, it’s easy to forget that the underlying model is still just predicting text.

1 0 0 14 0

View Details

Rohit Yadav @rohitdev_

2 months ago

Tip for doing Mathematical Calculations: Instead of asking an LLM to perform calculations directly on a dataset, ask it to write the Python code to do it for you. You can then run that code to get the actual results.

1 0 0 21 0

View Details

Rohit Yadav @rohitdev_

3 months ago

AI has turned coders into writers. The more articulate you are, the better coder you will be.

0 0 0 20 0

View Details

Rohit Yadav @rohitdev_

3 months ago

A lot of things have become possible due to vibe coding. Features that were earlier not worth investing time on can be shipped fast. It’s time when software would get more refined.

0 0 0 26 0

View Details

Rohit Yadav @rohitdev_

3 months ago

The bottleneck isn’t coding anymore. It’s thinking clearly enough to express what you want. Writing is now the highest leverage skill.

0 0 0 17 0

View Details

Rohit Yadav @rohitdev_

3 months ago

@googleaidevs Some serious prompting would have gone into it for sure otherwise we would have got another generic slop. Great if we can get prompts as well.

0 0 0 3K 0

View Details

Rohit Yadav @rohitdev_

3 months ago

Spent an hour debugging a deployment flow. Built it into a reusable skill. Now the same problem solves itself in 30 seconds. At scale: developers publish solutions as skills at a marketplace. AI agents discover and apply them instantly. Knowledge compounds automatically.