Sign in

Andrew Gross

@gross.systems
344 followers 3.2K following 319 posts

Engineer at YipitData. NYC Area github.com/andrewgross gross.systems I was told I had to add AI Engineer to my profile for the bots to find me. Views my own, not my employer etc etc.

PostsRepliesMedia
Andrew Gross @gross.systems · 19/08/2026
Trying to find an old video on Zip codes. No luck with Youtube search, SEO'd to oblivion. Ask Gemini, gives crappy results, prompt it for a Youtube link, no luck. Tell the model its part of Google and it can search Youtube, responds telling me it can't, but also includes the exact link I needed.
Screenshot of a conversation with Google Gemini about trying to find a video. The model responds that it can't search Youtube indexes directly and for me to give it more info on what to look for.  However, it also includes a link to the exact Youtube video I was searching for.  Its not linked in the text, or a reference, just the last thing in the message, completely unrelated to the text.
101
Andrew Gross @gross.systems · 20/06/2026
ianbarber.blog/2026/06/19/l... Sharing, if only for the reference to "Claude Telenovela"
Screenshot of blog entry: It’s tempting to assume that agents will Fix This: that you’ll hand your PyTorch or JAX definition to Claude Telenovela or whatever and have it generate optimally fused kernels2. To make that work you need a fixed, usable baseline to make sure that what is generated is… right.
101
Andrew Gross @gross.systems · 14/03/2026
Everyone one and a while you get to see the outside of the sampling curve on LLMs
A series of Agentic Read calls to the users home dir except one in the middle says anthropic instead of andrew
010
Andrew Gross @gross.systems · 20/02/2026
When did Claude Code auto memory start getting rolled out, cool as hell
Picture of the auto memory description text from https://code.claude.com/docs/en/memoryPicture of a claude code session where the agent decides to write to the MEMORY.md file for the project.
100
Andrew Gross @gross.systems · 09/01/2026
New requirement for monospace fonts: When coding agents draw diagrams the arrow lines are aligned.
ASCII/text flow chart with an arrow between nodes where the arrow character's shaft isnt quite aligned with the line character's height
000
Andrew Gross @gross.systems · 11/07/2025
@bsky.app UI Idea: It would be nice to be able to click in to the Alt Text prompt to be able to write the alt text directly (default for the first image I guess) instead of having to hit +Alt. It gets me every time.
000
Andrew Gross @gross.systems · 11/07/2025
@anthropic.com Major Bug, I think Claude Code prompting needs to be fixed so that it will state "Reticulating Splines..." when it is thinking
Claude Code thinking bar stating "Shucking..." and its duration and tokens per second.
100
Andrew Gross @gross.systems · 27/05/2025
Cursed Pyspark knowledge
Image showing that when passing a dictionary of data to be converted to a Pyspark dataframe with a defined schema, that column order only matters when using a Pandas dataframe. When passing just a dict of values order does not matter.
000
Andrew Gross @gross.systems · 06/01/2025
Bonus, I was testing on Nous Llama 3 8B, and the MIPROv2 optimizer added a funny set of stakes (similar to my grandma will die):
Screenshot of Prompt Text: In adhering to this structure, your objective is: 
        In a high-stakes scenario where a critical decision is being made about the containment of a pandemic, extract all contiguous tokens referring to specific people from a list of string tokens, including their names, titles, and affiliations. Output a list of tokens, without combining multiple tokens into a single value. This information is crucial for identifying key individuals involved in the decision-making process and understanding their roles.
100
Andrew Gross @gross.systems · 17/12/2024
Nice
P2P Perf of 50GB/s between two graphics cards after installing custom 4090 p2p driver
120
Andrew Gross @gross.systems · 11/12/2024
010
Andrew Gross @gross.systems · 27/11/2024
Every once and a while it will surprise you:
Histogram of confidence values with the vast majority at 0.85 and 0.9, but a single value at 0.0.
000
Andrew Gross @gross.systems · 27/11/2024
Guess I lied a little bit. Qwen did give some answers outside of 0.9 but also:
Histogram showing the distribution of confidence scores with a massive spike at 0.9 and minimal values at 0.8, 0.85 and 0.95
100
Andrew Gross @gross.systems · 14/11/2024
Add "half of star" to the list of things (like a completely full glass of wine) that ChatGPT can't generate
001
Andrew Gross @gross.systems · 13/09/2023
Sometimes Llama70b Chat gets a little touchy:
010