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.
Anyways, would need to reproduce it to understand more about it, but seems to try actually bridge the gap from math to real implementation via their algorithm.
November 1, 2025 at 2:58 PM
Anyways, would need to reproduce it to understand more about it, but seems to try actually bridge the gap from math to real implementation via their algorithm.
As for temperature, their work seems to focus on looking at the state of the token distribution for the last token. I think they arent looking to reverse each step of generation but instead take the state when the last token is generated and show you can get back to the prompt from there.
November 1, 2025 at 2:55 PM
As for temperature, their work seems to focus on looking at the state of the token distribution for the last token. I think they arent looking to reverse each step of generation but instead take the state when the last token is generated and show you can get back to the prompt from there.
Worth browsing the paper. They start with the mathematical approach ignoring some of the realities and showing that they are reversible. But they also build out an algorithm for being able to produce the input prompt based on a set of hidden states for a model.
November 1, 2025 at 2:53 PM
Worth browsing the paper. They start with the mathematical approach ignoring some of the realities and showing that they are reversible. But they also build out an algorithm for being able to produce the input prompt based on a set of hidden states for a model.
Context is also very poorly used in a couple ways. I feel like most tool calls etc need to be done in a sub agent with a concise summary returned to the main context (somehow not dropping important details). The info density of english tokens is bad and I can see using something else.
September 12, 2025 at 11:48 AM
Context is also very poorly used in a couple ways. I feel like most tool calls etc need to be done in a sub agent with a concise summary returned to the main context (somehow not dropping important details). The info density of english tokens is bad and I can see using something else.
Context retrieval is one of the worst areas right now. Since context fills up so fast, its hard to convey instructions effectively since most things fall off after 10-20k tokens. Not great to need to re import your claude md before every prompt.
September 12, 2025 at 11:46 AM
Context retrieval is one of the worst areas right now. Since context fills up so fast, its hard to convey instructions effectively since most things fall off after 10-20k tokens. Not great to need to re import your claude md before every prompt.
1mm context seems like a lot, and is in many ways, but it fills up extremely fast between code, prompts, instructions (claude md etc), tool descriptions, tool call results etc. We really need way more / a different system a la long term/short term memory. 100mm+ context to start
September 12, 2025 at 11:42 AM
1mm context seems like a lot, and is in many ways, but it fills up extremely fast between code, prompts, instructions (claude md etc), tool descriptions, tool call results etc. We really need way more / a different system a la long term/short term memory. 100mm+ context to start
I've tried using an lsp server with refactoring/renaming tools. It was great when Claude used it but the hardest part was getting Claude to actually use the MCP reliably. Probably a prompting issue. Could be fun to block the ability to use the Write() toolcall using Hooks and try to force it.
September 12, 2025 at 12:16 AM
I've tried using an lsp server with refactoring/renaming tools. It was great when Claude used it but the hardest part was getting Claude to actually use the MCP reliably. Probably a prompting issue. Could be fun to block the ability to use the Write() toolcall using Hooks and try to force it.
Some sort of digital sonder
September 9, 2025 at 4:37 PM
Some sort of digital sonder
Its surprising how bad the UX is on the Github UI for adding people to repos. Despite having people in our org with names matching the search prefix, Github loves to suggest random usernames who we have never interacted with. Super easy to accidentally add people.
September 9, 2025 at 2:46 PM
Its surprising how bad the UX is on the Github UI for adding people to repos. Despite having people in our org with names matching the search prefix, Github loves to suggest random usernames who we have never interacted with. Super easy to accidentally add people.