HN user

gregorymichael

4,994 karma

Developer Marketing at Google Cloud

http://baugues.com/

Posts781
Comments274
View on HN
tomasbjartur.substack.com 4mo ago

Customer Satisfaction Opportunities

gregorymichael
1pts0
www.astralcodexten.com 5mo ago

Moltbook: After the First Weekend

gregorymichael
3pts1
www.digitalocean.com 5mo ago

OpenClaw on Digital Ocean

gregorymichael
4pts0
allen.hutchison.org 6mo ago

Everything Becomes an Agent

gregorymichael
1pts1
www.politico.com 7mo ago

How Russia keeps raising an army to replace its dead

gregorymichael
10pts7
www.natesilver.net 8mo ago

LLMs are shockingly bad at poker

gregorymichael
2pts2
investinginai.substack.com 9mo ago

Why Google will win the AI race

gregorymichael
1pts0
dynomight.net 10mo ago

You can try to like stuff

gregorymichael
13pts1
obie.medium.com 1y ago

Claude on Rails

gregorymichael
4pts1
www.educationprogress.org 1y ago

Speedrun

gregorymichael
2pts0
dynomight.net 1y ago

The AI Safety Problem Is Wanting

gregorymichael
5pts1
dynomight.substack.com 1y ago

Futarky's Fundamental Flaw

gregorymichael
1pts0
infisical.com 1y ago

SSH Keys Don't Scale. SSH Certificates Do

gregorymichael
5pts1
simonwillison.net 1y ago

Building software on top of large language models

gregorymichael
36pts0
dynomight.net 1y ago

Trading Stuff for Money

gregorymichael
4pts0
dynomight.net 1y ago

Crémieux, J'accuse

gregorymichael
6pts0
www.thealgorithmicbridge.com 1y ago

AI doomers got the super intelligence thing all wrong

gregorymichael
2pts0
daveguarino.substack.com 1y ago

Benefits Navigation and the Potential for AI

gregorymichael
2pts0
medium.com 1y ago

The Future of Ruby and Rails in the Age of AI

gregorymichael
4pts0
dylanbeattie.net 1y ago

The Problem with Vibe Coding

gregorymichael
3pts0
simonwillison.net 1y ago

Model Context Protocol has prompt injection security problems

gregorymichael
4pts0
dynomight.net 1y ago

Limits of Smart

gregorymichael
1pts0
dynomight.substack.com 1y ago

Rewarding Ideas

gregorymichael
3pts0
www.haihai.ai 1y ago

Cursor vs. Claude Code

gregorymichael
2pts0
forum.cursor.com 1y ago

We've hit a rate limit with Anthropic

gregorymichael
11pts1
twitter.com 1y ago

Windsurf We Need to Talk

gregorymichael
2pts0
transformer-circuits.pub 1y ago

Insights on Cross-Coder Model Diffing

gregorymichael
1pts0
www.errormargin.com 1y ago

Time Travelling Life Insurance Arbitrage

gregorymichael
2pts0
dynomight.net 1y ago

Who exactly needs to get approval from an institutional review board (IRB)?

gregorymichael
211pts157
fireworks.ai 1y ago

Can DeepSeek R1 Teach Better Than Humans?

gregorymichael
1pts0

Just listened to the first suite. The Menuet was soulful and haunting. The Gigue was fierce and fascinating in contrast to Yo Yo Ma’s. I felt a profound sense of “there’s not enough time left in life to fully appreciate this piece of music.” Thank you for sharing.

I’m listening to this now for the first time now. Somehow I had never heard of him. Thank you. I sense this music will be with me for a long time.

I love this so much, as someone who tends to listen to a single piece of music on repeat (especially while coding) and has spent a lot of time with Yo-Yo Ma's "Six Evolutions".

Loved learning about the deep diversity of recordings from other artists, the ambiguous history of the music, and that there's a question if the music was even originally written for a cello!

Also loved that the site recommends different recordings based on the mood of interpretation.

This all reminds me of the HN favorite, "Reality has a lot of detail." Feel like I just discovered fractal complexity in a piece of music I naively thought I knew well.

One of my favorite AI How-tos in the last year. Barry and Erik spend 80% of the post saying ~”eh, you probably don’t need agents. Just build straightforward deterministic workflows with if-statements instead.”

And then, when you actually do need agents, don’t over complicate it!

This post also introduced the concept of an Augmented LLM — a LLM hooked up to tools, memory, data — which is a useful abstraction for evolving LLM use beyond fancy autocomplete.

“An augmented LLM running in a loop” is the best definition of an agent I’ve heard so far.

I have ADHD, and my daughter was recently diagnosed as well.

Been reflecting on this post as it's been soaking up the front page for the last 24 hours.

I want to commend you for shipping maybe the perfect HN post:

- Personal Journey

- Old school hardware

- DIY software

- Productivity hack

- Great title

- Quantified results (2-3x productivity) over non-trivial duration (few months)

- A low-effort offline solution that delivers real value for the 98% who will never build the thing

- Great polish on the reading experience with lots of little details

- Effective call to action (subscribe to get the software in a few weeks)

You inspired me to get my organization back on track. After researching receipt printers for 30 minutes, I realized what I actually need is to dust off the system that has worked for me in the past. But I'm picking up some post-its today and my daughter and I are going to try implementing your system for her over the weekend.

Thank you for putting the time into this!

Yes agreed. In most regions/groups in America, "you guys" does not carry the same meaning as "a group of guys"

Fun litmus test, if the person challenging this assertion happens to be a straight male: "how many guys have you slept with?"

"Sexist" does feel like too strong a word. "Gendered" perhaps more appropriate.

"Guys" is certainly gendered, so I understand folks feeling like "you guys" is as well.

Three-way group chats have been really great for me (as a 45 year old male) for keeping connection with my guy friends. Have a dozen of them or so. Small enough to still feel intimate. Big enough that someone replies / keeps the conversation going.

I've read all 20+ of the Jack Reacher books, some multiple times. Best bedtime reading I've found. Fun enough I actually want to go to bed. Shallow enough that if I miss a page or two because I'm drowsy, no big deal.