Rob Haisfield
banner
robhaisfield.com
Rob Haisfield
@robhaisfield.com
Building WebSim websim.com

Product thoughts: RobHaisfield.com

My research: ScalingSynthesis.com
July 10, 2025 at 2:41 PM
o3 and Claude give me analytics superpowers as a founder. I can do in an afternoon what would have taken me a week 3 years ago.

I put our database schema into context and it can write sql queries for any question, I run the queries, and the models can analyze / visualize the resulting CSVs.
July 8, 2025 at 3:02 AM
Is it just me or do a lot of SWEs have a findom relationship with Claude Code and Cursor?
June 25, 2025 at 5:13 PM
LinkedIn slop was already bad enough pre-AI lmao
June 22, 2025 at 2:54 PM
"Grok3 is the best language model, it's based"
March 4, 2025 at 12:42 AM
Happy Valentines Day! I made a social network for sharing what you love... and what you hate!

Made with o3-mini-high in websim. Post here: websim.ai/@rob/lovehat...
February 14, 2025 at 10:49 PM
Why do I still remember the password for my email address as a 10-year-old? Is that just taking up space in there? Is it load bearing?
February 3, 2025 at 8:41 PM
My dog had a nervous breakdown from me watching a show with a fire alarm beeping without headphones on.

These guys used to be wolves, what happened???
January 31, 2025 at 5:25 PM
With Deepseek R1, I'm really feeling my preference switch to reasoning models. I'm also using Flash 2.0 Thinking over Flash in Websim.

Comparing responses between Deepseek V3 and R1 really sold it for me. Wayyyy more depth to what's going on with R1.
Generally just trying to route all of my personal LLM usage to Deepseek R1 over the next couple of days to get a feel for it.

As a chatbot, it feels insightful, dutiful, creative, and extremely thorough. CoT is super cute, often more helpful than the answers.
January 31, 2025 at 12:30 AM
I think the novelty of reading the thinking for Deepseek R1 is gonna grow old pretty quick and people will go right back to ignoring 90% of the text the AI produces
Generally just trying to route all of my personal LLM usage to Deepseek R1 over the next couple of days to get a feel for it.

As a chatbot, it feels insightful, dutiful, creative, and extremely thorough. CoT is super cute, often more helpful than the answers.
January 30, 2025 at 1:55 PM
Generally just trying to route all of my personal LLM usage to Deepseek R1 over the next couple of days to get a feel for it.

As a chatbot, it feels insightful, dutiful, creative, and extremely thorough. CoT is super cute, often more helpful than the answers.
January 29, 2025 at 6:59 AM
Big takeway from the Deepseek R1 launch is that the visible CoT is super endearing
January 27, 2025 at 10:44 PM
how I prompt:
January 16, 2025 at 10:54 PM
@websim.bsky.social hey would you please change your username? would love to get the websim account set up
January 15, 2025 at 1:20 AM
I actually think regardless of benchmarks, Opus 3.5 would be substantially better than Sonnet 3.5 bc it could understand more instructions all at once, whereas websim users have gotten into the habit of giving Sonnet one thing at a time.
January 11, 2025 at 5:31 AM
My cousin in college told me he’s gonna get a ChatGPT Pro membership because “if I can’t make more than $200 a month from 20 second Sora videos I’ll cancel it.”

Never been prouder.
January 1, 2025 at 8:19 PM
Who do I follow for LLM discussions on here? Researchers, poasters, etc.
December 30, 2024 at 4:38 AM
It’s exceedingly obvious to me that we should make skilled immigration as easy as possible. Why wouldn’t we want talented people making money and paying taxes in the states? What founder wouldn’t want to be able to choose talent based on skill over location of birth?
December 27, 2024 at 4:43 AM
Anyone know of an email client that represents threaded email really well? Finding it kind of hard to search for specific emails and track conversations that branch off in a bunch of ways.
December 19, 2024 at 1:55 AM
The Gemini 2.0 Flash demo where you show it your computer screen and talk to it is awesome in concept, but whatever the system prompt is, it's annoying. It mostly narrates what it's seeing and hearing, like a toddler. Doesn't engage with the material. aistudio.google.com/live
December 16, 2024 at 5:48 PM
wouldn't it be crazy if Anthropic just cut their api prices in half??? so crazy.
December 11, 2024 at 12:20 AM
Buffalo wings and blue cheese are a delicacy in my culture
December 7, 2024 at 8:59 PM
real ones have their personal urls as their handles
December 6, 2024 at 8:52 PM
lmao everybody's dropping models this week (o1, Llama 3.3, Gemini 1.5) trying to one up each other...

will Anthropic join in now, or wait a few weeks until everyone has burned through their dry powder?
December 6, 2024 at 8:44 PM
Last night I said “I’m thankful for Claude 3.5 Sonnet” and my dad said “I’m thankful for all of my children, who are *unique* in their own way…”
November 29, 2024 at 4:11 PM