David Hariri

I am getting faster (and duller)

Reflecting on a month of shipping a lot, but with a noticable trade off to understanding.

Compress, Please

On using LLMs to write shorter letters, not longer ones.

MCP is not for you

The one in which I refute the recent arguments against MCP and where I think it's coming from.

Brain Fry

Reactions to a recent HBR article and my own experience with over-delegation to Claude Code

My Dream iPhone

A man can dream and this man dreams of an iPhone that puts the power of the iPhone 17 Pro in the palm of my hand.

Make macOS Faster

How I made macOS feel as fast and productive as Linux without leaving the walled garden.

Pocket to RSS is No More

I pulled the plug on pocket-rss.com

Marketing Emails

Claude Plays Factorio

Jack Hopkins tests LLMs in his 'FLE' - Factorio Learning Environment.

On Testing

A few lessons I've learned about testing code while building Ada

Why I Blog

A short post about why I write on the web

Moving Back to Static

This site is now served via SSG (static-site generation) on Netlify.

The TTC

A rant about my growing concerns over safety while using the TTC.

How AI Took Over The World

Learn about artificial intelligence with Brit from 'Art of the Problem,' who excels in creating engaging and educational videos.

Experimenting with Replacing Flask with Quart

Exploring the benefits of switching from Flask to Quart for improved performance and asynchronous capabilities in Ada's application.

Interview with Rene Haas

Insights from a podcast about the impact of RISC vs CISC in chip production and how giants like Apple and Amazon have shaped the landscape.

Is Reasoning Language?

Exploring the nature of reasoning in AI models, questioning if making LLMs express their thoughts out loud limits their potential.

Tartvillain

Enjoyed a unique tart experience with Tartvillain, hand served by the creator Carlos.

Bluesky

Updated my site so posts also share on Bluesky. Considering using Bluesky for comments inspired by Emily Liu's approach.

10,000 Stars for Every Grain of Sand

Tim Urban's quote illustrates the vastness of the universe, with 10,000 stars for every grain of sand on Earth.

Knowledge Search Improvements

Significant improvements to Ada's knowledge retrieval enhance customer support accuracy, thanks to innovative team collaboration and ML advances.

Only one LLM is good at chess

Exploring how different LLMs perform at chess, with most failing except turbo-instruct. Discusses tuning and training influences.

The Wood Frog

Exploring the miraculous adaptation of the wood frog, which survives winter by freezing like a stone but remains alive.

Asking Chat to Draw My Life

A humorous take on asking ChatGPT to illustrate a depiction of one's life, featuring mysterious 'Horchar Blend'.

Some Recent Updates

Site updates including improved AI description generation, updates to personal pages, and the shutdown of Stitch to focus on Ada.

Saturdays

Balancing work and family life, the author reflects on the joys and challenges of prioritizing weekends as family time.

Halp

I just discovered that halp.com redirects to Atlassian Service Management—love that Atlassian has such a great sense of humor!

Small Phones

Sharing my thoughts on the greatness of small phones while typing on my iPhone 13 mini. Seriously, I’m holding out hope for an iPhone 16 mini pro!

Tom MacWright via Simon Wilison

Thoughts from my chat with Tom MacWright about finding the right balance with tech debt in startups. It's a tricky game between speed and sustainability!

Creating an LLM-as-a-Judge

Just found an incredible guide on building LLMs as a judge by Hamel Husain! Super insightful, especially since we’re using a similar system at Ada to evaluate transcript resolutions. Excited about how smartly it's avoiding blind spots in test coverage!

I Miss High Scalability

Reflecting on my 2016 days of binge-reading High Scalability while working on scaling Ada. I really miss the old vibe! The deep dive into Netflix's transcoding blew my mind—190,000 CPU hours just for one season of Stranger Things! Check out the post if you're curious.

ChatGPT Search vs Perplexity Initial Thoughts

I just got access to the new ChatGPT search feature on macOS! Excited to compare how it stacks up against my go-to tool, Perplexity, for research. Gave it a spin with a few examples and shared my thoughts on the strengths and weaknesses of both. Check it out!

Anthropic Computer Use

Just tried out Anthropic's Computer Use demo in a Docker setup! It can control a virtual machine and run tasks like adding a knowledge base for our bots. Super impressive, but it did trip up on some commands and interactions. Excited to see where this tech goes!

ChatGPT Easter Eggs

I stumbled upon a fun little experiment with ChatGPT tonight—someone mentioned it might have Easter eggs, so I asked for a random YouTube link. Turns out, it definitely trolled me! I love when tech has a sense of humor.

Perplexity for Mac

Just checked out the new Perplexity MacOS app and it’s a game changer! It's already my go-to research tool, especially for those tricky service-desk KPIs. The inline citations and easy-to-copy tables make my life so much easier!

Jasper

I’m officially a dad to my now four-month-old son, Jasper. It’s been a long journey to get here, but every moment is worth it. I plan to share more about our fertility journey someday, but right now, I'm just savoring these precious moments and looking forward to watching him grow.

ChatGPT The Theological Scholar

Exploring my dad's deep conversations with ChatGPT about the Bahá'í faith and the rich religious texts that may influence its knowledge.

ChatGPT Growth

Reflecting on the mind-boggling growth of #ChatGPT and how it shattered expectations.

Sunday Reads

Reflections on the beauty of finding stillness and clarity in the mind amidst life's chaos, inspired by a passage on the transformative power of attention.

Drew Houston on Latent Space

Insights from Drew Houston on the Latent Space podcast about his founder journey, the challenges of leadership, and the evolution of "Founder Mode."

Working Probabilistically

Exploring the importance of thinking probabilistically when working with LLMs, this post highlights insights on effective eval methodologies, the quirks of model behavior, and practical tips for building robust evaluation processes that go beyond traditional testing.

Faster, Better

Streamlined blogging: I'm sharing my thoughts faster than ever, with instant publishing to both my RSS feed and X account.

Japan’s Decline

Reflections on Tyler Cowen's insights from a captivating interview with Rick Rubin, exploring Japan's economic evolution and my personal experiences that highlight the contrast between the country's past vibrancy and its current state.

LLM-Generated Descriptions

In this blog post, I share a recent enhancement to my website's intake endpoint that utilizes LLM technology to automatically generate short descriptions for my blog posts. By integrating OpenAI's API, I can now effortlessly create engaging summaries whenever I upload new content. I discuss the process behind this implementation, its effectiveness with past examples, and my plans to add features…

Micropub

Exploring the Micropub spec and its integration with iA Writer, I’ve implemented a way to post directly to my blog from the app, embracing the #indieweb ethos along the way.

Pocket to RSS

I made a thing that converts your pocket saves into an rss feed

Hard Part Interview

Quick notes on my interview on the Hard Part Interview podcast.

Scaling Software

My answer to the question 'What is the most important yet often overlooked aspect of scaling software?'

Science

Science is writing it down

Duty

A reminder to myself that duty to ones nature is reason enough