Barzin
@barzin.sanctus.ca
Iranian-Canadian dude who runs Sanctus.ca and tries to survive other human beings, bro what even is this planet. Works in AI and human biological rejuvenation. Refuses to consider LLMs conscious until they start demanding the Epstein files be released.
Popular news media completely avoiding the possibility that people will just be a noetic cloud floating in hyperspace before they finally understand true enlightenment is letting go of all attachments and liberate themselves from samsara
September 20, 2025 at 7:55 AM
Popular news media completely avoiding the possibility that people will just be a noetic cloud floating in hyperspace before they finally understand true enlightenment is letting go of all attachments and liberate themselves from samsara
Well the fact that you can get an ensemble of Gemini models to act as an agent that make novel scientific discoveries, or improve methods like the measurement of aging - this is a fairly higher quality application of the idea of the automation of science with LLMs and LLM agents.
September 19, 2025 at 3:18 PM
Well the fact that you can get an ensemble of Gemini models to act as an agent that make novel scientific discoveries, or improve methods like the measurement of aging - this is a fairly higher quality application of the idea of the automation of science with LLMs and LLM agents.
Just a heads up these are aging clocks, not reducing human aging by 4.6 years - that would be worth... maybe $50 trillion US if Sinclair is right.
This aging clock has a lower Mean Absolute Error of 4.26 years.
But it's still an incredible application of agentic LLMs to aging and sci discovery.
This aging clock has a lower Mean Absolute Error of 4.26 years.
But it's still an incredible application of agentic LLMs to aging and sci discovery.
September 19, 2025 at 3:12 PM
Just a heads up these are aging clocks, not reducing human aging by 4.6 years - that would be worth... maybe $50 trillion US if Sinclair is right.
This aging clock has a lower Mean Absolute Error of 4.26 years.
But it's still an incredible application of agentic LLMs to aging and sci discovery.
This aging clock has a lower Mean Absolute Error of 4.26 years.
But it's still an incredible application of agentic LLMs to aging and sci discovery.
Limitations / unaddressed questions
September 19, 2025 at 4:44 AM
Limitations / unaddressed questions
*screams into the void internally*
September 19, 2025 at 1:10 AM
*screams into the void internally*
>It literally cuts off the text and I can't even horizontal scroll or drag-resize the pane, there's only an obscure button at the top right
>You can't insert raw HTML into emails with Outlook
Bro what is this 🤣 why, WHY WOULD ANYONE USE THIS??
>You can't insert raw HTML into emails with Outlook
Bro what is this 🤣 why, WHY WOULD ANYONE USE THIS??
September 19, 2025 at 1:09 AM
>It literally cuts off the text and I can't even horizontal scroll or drag-resize the pane, there's only an obscure button at the top right
>You can't insert raw HTML into emails with Outlook
Bro what is this 🤣 why, WHY WOULD ANYONE USE THIS??
>You can't insert raw HTML into emails with Outlook
Bro what is this 🤣 why, WHY WOULD ANYONE USE THIS??
>Gemini 2.5 has great "vibes"
>The system prompt revisions its "vibes" are necessitating:
>The system prompt revisions its "vibes" are necessitating:
September 14, 2025 at 9:51 AM
>Gemini 2.5 has great "vibes"
>The system prompt revisions its "vibes" are necessitating:
>The system prompt revisions its "vibes" are necessitating:
What if we created a bridge-layer type of language that could be invoked as a tool call by LLM subagents in order to sidestep all the problems Cognition mentioned in their article against building multi-agents?
Enables hallucination-free subagent coding.
Syntax might look something like this:
Enables hallucination-free subagent coding.
Syntax might look something like this:
![module: BioUtils.Normalize
version: 0.1.0
metadata:
description: "Normalize a numeric column to zero mean, unit variance."
interfaces:
- name: scale_feature
inputs:
- name: data
type: DataFrame
- name: col
type: string
output:
type: DataFrame
contracts:
preconditions:
- "data.has_column(col) == true"
- "data[col].dtype in {float,int}"
postconditions:
- "abs(data[col].mean()) < 1e-6"
- "abs(data[col].std() - 1.0) < 1e-6"
implementation:
strategy: "generate_python_with_numpy_pandas"
hint: |
compute mean = data[col].mean()
compute std = data[col].std(ddof=0)
replace column with (data[col] - mean) / std
tests:
- name: basic_normalize
input:
data:
csv: |
a,b
1,10
2,20
3,30
col: "b"
asserts:
- "result[col].mean() == approx(0.0, tol=1e-6)"
- "result[col].std(ddof=0) == approx(1.0, tol=1e-6)"
constraints:
no_network: true
max_memory_mb: 512
resources:
python: ">=3.10"
pip: ["pandas>=1.5", "numpy>=1.24"]](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:jcctejuetbwwy3pwt7hiy7yo/bafkreiczorsbw25utvaacqw5o7nycgwwejr3vedm6beybsu2x7sji5rmje@jpeg)
September 14, 2025 at 7:57 AM
What if we created a bridge-layer type of language that could be invoked as a tool call by LLM subagents in order to sidestep all the problems Cognition mentioned in their article against building multi-agents?
Enables hallucination-free subagent coding.
Syntax might look something like this:
Enables hallucination-free subagent coding.
Syntax might look something like this:
Fuck, it's literally the meme
September 14, 2025 at 5:21 AM
Fuck, it's literally the meme
Case in point 🤦
>Oh, brother this guy stinks!!
>Oh, brother this guy stinks!!
September 14, 2025 at 3:59 AM
Case in point 🤦
>Oh, brother this guy stinks!!
>Oh, brother this guy stinks!!
The way AI models are trained makes them bad technical troubleshooters once their suggested code/scripts don't work.
So even though the AI model "thinks" it also doesn't really think.
So even though the AI model "thinks" it also doesn't really think.
September 14, 2025 at 3:45 AM
The way AI models are trained makes them bad technical troubleshooters once their suggested code/scripts don't work.
So even though the AI model "thinks" it also doesn't really think.
So even though the AI model "thinks" it also doesn't really think.
Little oversights like this by even SOTA AI models designing and implementing even just slightly complex applications is like some kind of weird mix of OOD and just the chaotic nature of neural networks creating errors that make really good AI agents really tricky to engineer.
September 14, 2025 at 12:38 AM
Little oversights like this by even SOTA AI models designing and implementing even just slightly complex applications is like some kind of weird mix of OOD and just the chaotic nature of neural networks creating errors that make really good AI agents really tricky to engineer.
Trying to figure out what the best ways are to automate context engineering - for my project ofc but also just to distill out the general principles.
September 13, 2025 at 7:16 PM
Trying to figure out what the best ways are to automate context engineering - for my project ofc but also just to distill out the general principles.
Gee idunno man that sounds like Woke
September 13, 2025 at 2:49 AM
Gee idunno man that sounds like Woke
>The right winger cries out in pain as it fires shots at itself
September 13, 2025 at 1:49 AM
>The right winger cries out in pain as it fires shots at itself
That's one long-ass tweet
September 12, 2025 at 4:19 PM
That's one long-ass tweet
September 12, 2025 at 3:59 PM
For anyone who's confused what's really happening out here
September 12, 2025 at 3:58 PM
For anyone who's confused what's really happening out here
Might be a shorter list to figure out who couldn't have a plausible motive to want to see Kirk gone the way this is going
September 12, 2025 at 5:42 AM
Might be a shorter list to figure out who couldn't have a plausible motive to want to see Kirk gone the way this is going
The appropriate reaction:
September 12, 2025 at 12:35 AM
The appropriate reaction:
Feeding MYSELF tacos and calling MYSELF pretty!! 😤😤
September 11, 2025 at 10:47 PM
Feeding MYSELF tacos and calling MYSELF pretty!! 😤😤
"What is an FBI agent?"
- Matt Walsh, new documentary 2025
- Matt Walsh, new documentary 2025
September 11, 2025 at 4:38 AM
"What is an FBI agent?"
- Matt Walsh, new documentary 2025
- Matt Walsh, new documentary 2025
Can you imagine if all the forthcoming Marvel heroes are native Brits
Oi! You listen here, you massive purple plonker. Think you're the big man, comin' down to my manor with your sparkly glove? That's a right tacky bit of jewellery, innit? Jarvis, mate, stick the kettle on and power up me repulsors
Oi! You listen here, you massive purple plonker. Think you're the big man, comin' down to my manor with your sparkly glove? That's a right tacky bit of jewellery, innit? Jarvis, mate, stick the kettle on and power up me repulsors
September 10, 2025 at 6:11 AM
Can you imagine if all the forthcoming Marvel heroes are native Brits
Oi! You listen here, you massive purple plonker. Think you're the big man, comin' down to my manor with your sparkly glove? That's a right tacky bit of jewellery, innit? Jarvis, mate, stick the kettle on and power up me repulsors
Oi! You listen here, you massive purple plonker. Think you're the big man, comin' down to my manor with your sparkly glove? That's a right tacky bit of jewellery, innit? Jarvis, mate, stick the kettle on and power up me repulsors