Andrew Gross
@gross.systems
Engineer at YipitData.
NYC Area
https://github.com/andrewgross/
https://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.
NYC Area
https://github.com/andrewgross/
https://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.
Can't wait for the Open Weight models to finish distilling Opus 5.5 so they can produce legible descriptions again.
September 29, 2026 at 1:26 AM
Can't wait for the Open Weight models to finish distilling Opus 5.5 so they can produce legible descriptions again.
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 Language Models | Notion
A System One Model for Fast and Generalizable Decision-Making
contrastive-lm.notion.site
September 24, 2026 at 12:07 PM
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.
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.
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.
docs.github.com
September 10, 2026 at 5:57 PM
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.
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..
September 10, 2026 at 5:54 PM
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..
With the way devices are going these days, Im going to need to have all of my private convos inside an MRI machine.
September 10, 2026 at 1:09 PM
With the way devices are going these days, Im going to need to have all of my private convos inside an MRI machine.
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
August 23, 2026 at 2:44 AM
Claude has reduced me to forcing it to summarize its own output without jargon every time it comes back to me. github.com/andrewgross/...
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.
August 19, 2026 at 3:23 PM
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.
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.
August 15, 2026 at 4:29 PM
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.
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.
August 7, 2026 at 7:06 PM
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.
Spaghettios Aglio e Olio
July 29, 2026 at 2:19 AM
Spaghettios Aglio e Olio
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.
July 27, 2026 at 2:17 PM
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.
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.
July 18, 2026 at 12:27 AM
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.
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.
July 16, 2026 at 1:14 AM
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.
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.
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.
www.npmjs.com
July 14, 2026 at 12:51 PM
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.
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.
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/...
Original: github.com/jehna/humanify
Mine: github.com/andrewgross/...
GitHub - jehna/humanify: Deobfuscate Javascript code using ChatGPT
Deobfuscate Javascript code using ChatGPT. Contribute to jehna/humanify development by creating an account on GitHub.
github.com
July 13, 2026 at 1:07 AM
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/...
Original: github.com/jehna/humanify
Mine: github.com/andrewgross/...
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.
July 10, 2026 at 2:03 PM
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.
TIL the etymology of cybernetics (and cyber). Thats... actually pretty cool. en.wikipedia.org/wiki/Cyberne...
June 20, 2026 at 6:16 PM
TIL the etymology of cybernetics (and cyber). Thats... actually pretty cool. en.wikipedia.org/wiki/Cyberne...
June 20, 2026 at 6:12 PM
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.
June 19, 2026 at 1:54 AM
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.
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
June 18, 2026 at 2:03 PM
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
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...
Deep Learning with Yacine
Deep learning project and theory videos every week! 👺
www.youtube.com
June 17, 2026 at 2:19 PM
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...
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.
June 15, 2026 at 2:40 AM
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.
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.
June 9, 2026 at 5:45 PM
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.
Dead Internet Theory, but for recruiting
June 5, 2026 at 2:45 AM
Dead Internet Theory, but for recruiting
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.
May 18, 2026 at 1:42 PM
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.