Sign in

Andrew Gross

@gross.systems
343 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 · 29/09/2026
Can't wait for the Open Weight models to finish distilling Opus 5.5 so they can produce legible descriptions again.
040
Andrew Gross @gross.systems · 24/09/2026
contrastive-lm.notion.site Interesting write up. No paper yet unfortunately. If some of the claims hold true it would be a pretty incredible leap. Their SOTA DeepSWE scores come from generating rollouts using Opus/Fable and then using their model to select the "right" action.
contrastive-lm.notion.site
Contrastive Language Models | Notion
A System One Model for Fast and Generalizable Decision-Making
200
Andrew Gross @gross.systems · 10/09/2026
Pondering using docs.github.com/en/repositor... this to hide away code where the agent has domain, so PRs only focus on the interfaces and hotspots I care about.
docs.github.com
Customizing how changed files appear on GitHub - GitHub Docs
To keep certain files from displaying in diffs by default, or counting toward the repository language, you can mark them with the linguist-generated attribute in a .gitattributes file.
000
Andrew Gross @gross.systems · 10/09/2026
Im wondering if the next big "change" we see from AI is in our bureaucracy. Not so much in how it operates internally, but in the dramatic rise in inputs from people using AI. So many things were implicitly gated by the cost of time and attention that has mostly gone away. Filing complaints, forms..
100
Andrew Gross @gross.systems · 10/09/2026
With the way devices are going these days, Im going to need to have all of my private convos inside an MRI machine.
000
Andrew Gross @gross.systems · 23/08/2026
Claude has reduced me to forcing it to summarize its own output without jargon every time it comes back to me. github.com/andrewgross/...
github.com
050
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 · 15/08/2026
Im curious what the uncounted token overhead is for things like ChatGPT and Claude chat sessions. There are a lot of things like memory that involve some background LLM processing that don't seem to get reflected in usage limits, I wonder if it dramatically affects margin.
110
Andrew Gross @gross.systems · 07/08/2026
The latest crop of Claude models are too verbose and create incredible amounts of unnecessary jargon, requiring a re-prompt just to clean it up. Curious if its a side effect of RL rewarding lower response length, so they "create" vocabulary to compact more into less. Either way it sucks.
000
Andrew Gross @gross.systems · 29/07/2026
Spaghettios Aglio e Olio
000
Andrew Gross @gross.systems · 27/07/2026
Im curious if I have missed papers/projects out there for converting compiled/minified code to an AST/text code consistently. I know of humanify of course, and I found the BinDiff paper/project as well. Wondering what else is out there. My big problem right now is consistency between versions.
110
Andrew Gross @gross.systems · 18/07/2026
How often do people get the prompt in CC asking if Anthropic can review their session to help improve Claude Code? I haven't gotten it on my work setup, but on my personal sub I have seen it prob 4-5 times. This is on a project that gets downgraded from Fable to Opus probably 50% of the time.
010
Andrew Gross @gross.systems · 16/07/2026
Fable seems to be really good at... deciding it needs to spin up 10 sub-agents, immediately running out of usage credits, being awoken and then deciding to do all the work itself while doing a bad job.
010
Andrew Gross @gross.systems · 14/07/2026
Something really weird is going on with the npm downloads counter for claude-code www.npmjs.com/package/@ant... Really weird spikes and total download counts in recent versions, while old versions have 1000s or even just 100s of downloads. No way every one is on the native installer.
npmjs.com
010
Andrew Gross @gross.systems · 13/07/2026
Im realizing my fork of humanify has become quite a different beast than the original repo, and I need a new name (while still giving credit to the original). Original: github.com/jehna/humanify Mine: github.com/andrewgross/...
github.com
GitHub - jehna/humanify: Deobfuscate Javascript code using ChatGPT
Deobfuscate Javascript code using ChatGPT. Contribute to jehna/humanify development by creating an account on GitHub.
000
Andrew Gross @gross.systems · 10/07/2026
The only thing I ever (rarely) use image generation for is making a customized meme for my friends. It seems that Google has decided that making a meme is a copyright violation and can't work with it at all.
010
Andrew Gross @gross.systems · 20/06/2026
TIL the etymology of cybernetics (and cyber). Thats... actually pretty cool. en.wikipedia.org/wiki/Cyberne...
en.wikipedia.org
Cybernetics - Wikipedia
130
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 · 19/06/2026
FrontierCode is great and all, but does anyone actually get to run it? Aside from the Fable release, I haven't heard of any updates for the rankings for any new models.
000
Andrew Gross @gross.systems · 18/06/2026
I need to make AngryBench. Just re-running/validating existing model benchmarks, but adding in a system message or prompt prefix to set the tone of the interaction from the user (angry, kind, professional etc). Essentially trying to understand how various models perform based on how you treat them
000
Andrew Gross @gross.systems · 17/06/2026
Apropros of nothing, shoutout to Deep Learning with Yacine. Great channel where someone recently graduated and a research background just...talks to the authors of papers. Its great www.youtube.com/@deeplearnin...
youtube.com
Deep Learning with Yacine
Deep learning project and theory videos every week! 👺
000
Andrew Gross @gross.systems · 15/06/2026
I find myself needing to expand Github PR diffs much further these days to be able to actually see the relevant code for understanding it. The way agents craft code, with excessive commenting/explanation and poor abstraction/overlong methods makes it hard to visually see everything easily.
100
Andrew Gross @gross.systems · 09/06/2026
With the release of Mythos and Fable, I'm betting Anthropic goes with Saga and Epic for their next two big models. And yarn for their small model.
230
Andrew Gross @gross.systems · 05/06/2026
Dead Internet Theory, but for recruiting
100
Andrew Gross @gross.systems · 18/05/2026
The easiest way to find out if another company thinks you are a competitor is to see if they buy out the top ad spot when your search for your own name.
000
Reposted by Andrew Gross
Ethan @ethanrosenthal.com · 15/05/2026
this is wild damnlines.com
damnlines.com
damnlines — Live Wait Times & Line Tracker for NYC
No one likes waiting in a damn line. Track live line activity for NYC restaurants and venues with real-time queue snapshots and wait-time signals. No one likes waiting in a damn line.
1121
Reposted by Andrew Gross
Phillip Carter @phillipcarter.dev · 11/05/2026
Oh shit, this Thinking Machines update looks wild thinkingmachines.ai/blog/interac...
thinkingmachines.ai
Interaction Models: A Scalable Approach to Human-AI Collaboration
Interaction models move beyond turn-based AI interfaces by handling multimodal, real-time collaboration natively across audio, video, and text.
023
Andrew Gross @gross.systems · 08/05/2026
Chrome's built in LLM, but you just use it for properly filling in credit card and address forms.
010
Andrew Gross @gross.systems · 24/04/2026
You'd think with all these fancy agentic coding models Zoom could make a client that could start in less than 30 seconds.
000
Andrew Gross @gross.systems · 26/03/2026
Somehow slack is using more memory for text only office chat, than an entire docker container.
130
Andrew Gross @gross.systems · 24/03/2026
With all the agent stuff heating up one thing that would be really nice is to be able to create sessions with dynamically downscoped creds. Ex: instead of my full sql perms, the session just has "read only for X,Y,Z and write to A,B,C". They key being that I can generate any subset of my perms
100
Andrew Gross @gross.systems · 18/03/2026
I'll believe we have AGI when companies start shipping native apps instead of Electron everywhere.
000
Andrew Gross @gross.systems · 14/03/2026
In TPUs, my impression is that weights are "stationary" and data is (systolically) moved over them, while a GPU has weights and data brought together, combined, and flushed. In a world of large MoE models, do TPUs have a disadvantage because they will need to move around more weights than before?
100
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 · 01/03/2026
The combination of Skills w/ the ease of creating your own "bespoke" software feels a lot better than MCP servers (or even using most skills from other folks). Seems way more effective to create some tight minimal skills/scripts for things than plug in a whole MCP api surface.
100
Andrew Gross @gross.systems · 26/02/2026
Has anyone seen support for things like "remote skills" for Claude Code or similar? Its a bit different from MCP in that its not just calling a regular API endpoint. Im thinking something closer to how the Web Search tool works, where its really a mini remote agentic system returning results.
100
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 · 07/02/2026
For the next big jump for coding agents, I think the frontier labs are going to spend a lot of effort on making them good and creating their own problem specific harness for iterating.
100
Andrew Gross @gross.systems · 07/02/2026
I have a sneaking suspicion time travel debuggers are going to come back in to vogue once they are made legible to agents.
110
Andrew Gross @gross.systems · 07/02/2026
Getting agents to run experiments where you need to trade off feature optimization with running time optimization is tough. Agents don't experience linear time and don't have a "feeling" that they need to spend time optimizing to iterate faster.
100
Andrew Gross @gross.systems · 01/02/2026
There's no reason the "Movie" Toothbrushing song on the Yoto has to go that hard.
010
Andrew Gross @gross.systems · 29/01/2026
LLMs can be great for those cases (in coding at least) where you assume there is a body of work around a problem, but you don't know the terminology to find it. In the past you just had to Google and hope, or ask a coworker. Still possible to fail with LLMs but can be easier.
100
Andrew Gross @gross.systems · 27/01/2026
Github Stars are a very salient example of Goodhart's law right now.
020
Andrew Gross @gross.systems · 22/01/2026
My kingdom for sparse mxfp4 kernels in FlashInfer for sm120
010
Andrew Gross @gross.systems · 13/01/2026
I want to figure out a harness so that I can run Claude Code against a Kaggle competition. I feel like it could pretty reliably score silver in many competitions, assuming it was given access to the forums and had a decent harness
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 · 08/01/2026
I used to think that typing speed beyond a certainly level had diminishing returns for programming. That said, it seems like there is a lot of value in being able to quickly convey prompts via typing, as voice transcription lacks some capabilities for things like linking files or code.
020
Andrew Gross @gross.systems · 07/01/2026
I remember a while back there was a lot of discourse around codebases that are "greppable" vs those that are expected to be navigated with an IDE. Seems like greppable ended up being the correct choice for coding agents (at leat for now).
020
Andrew Gross @gross.systems · 12/12/2025
Trying out a new thing: "This code dictated but not read" to absolve myself of all responsibility for LLM generated code, just like executives in the 60s would place all the blame for their bad ideas on their secretary.
010
Andrew Gross @gross.systems · 02/12/2025
Release PySpark Toolkit 0.5.0: * support for S3 Presigned URLs in Pure Pyspark * `fdtf` - A generic UDTF decorator that can wrap an arbitrary row level python function and append its results as columns to your dataframe. Cuz UDTFs are annoying to use.
100