Articles for category: AI Tools

March 15, 2025

ikayaniaamirshahzad@gmail.com

How do I speed up my agent?

I get this question a bunch. Developers generally first spend time getting the agent to work, but then they turn their attention to speed and cost. There are few things we see developers doing: Identifying where the latency is coming from Changing the UX to reduce the “perceived” latency Making fewer LLM calls Speeding up LLM calls Making LLM calls in parallel Identifying where the latency is coming from This may sound basic, but how you approach reducing latency will depend entirely on your specific bottleneck. Is the latency coming from one big LLM call, or from multiple small ones

March 15, 2025

ikayaniaamirshahzad@gmail.com

GPT-4 Is a Reasoning Engine (2023)

Sponsored By: Bessemer Venture Partners This essay is brought to you by Bessemer Venture Partners, a leading venture capital firm investing in artificial intelligence. Discover how AI is transforming industries and creating new entrepreneurial opportunities with their latest free ebook, Everything, Everywhere, All AI. Dive into strategies and real-world case studies that will help you stay ahead of the AI revolution. Ready for the AI era? Large language models aren’t always right. Their strength—for now—is mimicry and prediction rather than accuracy. But as Dan Shipper writes in this essay from March 2023, these models are only as good as the

March 15, 2025

ikayaniaamirshahzad@gmail.com

A quote from Andrew Ng

Some people today are discouraging others from learning programming on the grounds AI will automate it. This advice will be seen as some of the worst career advice ever given. I disagree with the Turing Award and Nobel prize winner who wrote, “It is far more likely that the programming occupation will become extinct […] than that it will become all-powerful. More and more, computers will program themselves.”​ Statements discouraging people from learning to code are harmful! In the 1960s, when programming moved from punchcards (where a programmer had to laboriously make holes in physical cards to write code character

March 15, 2025

ikayaniaamirshahzad@gmail.com

Release notes for Deephaven version 0.33.0

Deephaven Community Core version 0.33.0 is now out. We’re excited about it and hope you will be too after reading the release notes! Let’s take a closer look at what it includes. Read Parquet from AWS S3​ Deephaven can now read single Parquet files from AWS S3. The code block below fetches data from a public S3 bucket. This new experimental feature is under active development, so stay tuned for future developments as we expand on it. from deephaven import parquetfrom deephaven.experimental import s3from datetime import timedeltadrivestats = parquet.read( "s3://drivestats-parquet/drivestats/year=2023/month=02/2023-02-1.parquet", special_instructions=s3.S3Instructions( "us-west-004", endpoint_override="https://s3.us-west-004.backblazeb2.com", anonymous_access=True, read_ahead_count=8, fragment_size=65536, read_timeout=timedelta(seconds=10), ),) Rollup table

March 15, 2025

ikayaniaamirshahzad@gmail.com

Data Machina #248 – Data Machina

Jailbreaking AI Models: It’s easy. Hundreds of millions of dollars have been thrown at AI Safety & Alignment over the years. Despite that, jailbreaking LLMs in April 2024 is easy. Oddly enough, as the LLM models become more capable and sophisticated, the jailbreaking attacks are becoming easier to perform, more effective, and frequent. Gary Marcus – who is hypercritical about LLMs and current AI trends- just published this very opinionated post: An unending array of jailbreaking attacks could be the death of LLMs. I often speak to colleagues and clients about the “LLM jailbreaking elephant in the room.” And they

March 15, 2025

ikayaniaamirshahzad@gmail.com

What We’ve Learned From A Year of Building with LLMs – Applied LLMs

Here, we share best practices for core components of the emerging LLM stack: prompting tips to improve quality and reliability, evaluation strategies to assess output, retrieval-augmented generation ideas to improve grounding, how to design human-in-the-loop workflows, and more. While the technology is still nascent, we trust these lessons are broadly applicable and can help you ship robust LLM applications. Prompting We recommend starting with prompting when prototyping new applications. It’s easy to both underestimate and overestimate its importance. It’s underestimated because the right prompting techniques, when used correctly, can get us very far. It’s overestimated because even prompt-based applications require

March 15, 2025

ikayaniaamirshahzad@gmail.com

Domain Driven Design – DEV Community

DDD is a software design approach that prioritizes the business domain at the core of development. Coined by Eric Evans in his book Domain-Driven Design: Tackling Complexity in the Heart of Software, DDD helps teams structure code based on real-world business concepts, making applications easier to understand and evolve. Key Goals of DDD Align software with real business problems Improve communication between developers and domain experts Reduce complexity by organizing code around business concepts Facilitate maintainability and scalability “In order to create good software, you have to know what that software is all about. You cannot create a banking software

March 15, 2025

ikayaniaamirshahzad@gmail.com

a deep dive · Explosion

PDFs are ubiquitous in industry and daily life. Paper is scanned, documents are sent and received as PDF, and they’re often kept as the archival copy. Unfortunately, processing PDFs is hard. In this blog post, I’ll present a new modular workflow for converting PDFs and similar documents to structured data and show how to build end-to-end document understanding and information extraction pipelines for industry use cases. With more powerful Vision Language Models (VLMs), it’s finally become viable to complete many end-to-end tasks using PDFs as inputs, like question answering or more classic information extraction. This makes it tempting to consider

March 15, 2025

ikayaniaamirshahzad@gmail.com

Fine-tune FLUX.1 to create images of yourself

The FLUX.1 family of image generation models was released earlier this month and took the world by storm, producing images surpassing the quality of existing open-source models. The community quickly started to build new capabilities on top of Flux, and not long after the release we announced Flux fine-tuning support on Replicate. Fine-tuning Flux on Replicate is easy: you just need a handful of images to get started. No deep technical knowledge is required. You can even create a fine-tune entirely on the web, without writing a single line of code. The community has already published hundreds of public Flux