Juraj
@aksuno.bsky.social
Freelance software engineer, AI/ML researcher, and co-founder of https://vectorsight.net. Also rock-climber and occasional runner.
Every product owner or whoever manages feature descriptions in backlog should start vibe-coding. If you find yourself frustrated and struggling to describe the feature to the state-of-the-art coder model, please, stop for a while and think about how devs working with you must feel.
August 22, 2025 at 9:33 PM
Every product owner or whoever manages feature descriptions in backlog should start vibe-coding. If you find yourself frustrated and struggling to describe the feature to the state-of-the-art coder model, please, stop for a while and think about how devs working with you must feel.
The LLM prompt is basically a set of constraints as in a constraint programming problem.
The more details (constraints) are in your prompt, the less improvisation (and hallucination) will occur. This is direct analogy to solver landing in the local minima on the wrong side of search space.
The more details (constraints) are in your prompt, the less improvisation (and hallucination) will occur. This is direct analogy to solver landing in the local minima on the wrong side of search space.
May 24, 2025 at 5:36 PM
The LLM prompt is basically a set of constraints as in a constraint programming problem.
The more details (constraints) are in your prompt, the less improvisation (and hallucination) will occur. This is direct analogy to solver landing in the local minima on the wrong side of search space.
The more details (constraints) are in your prompt, the less improvisation (and hallucination) will occur. This is direct analogy to solver landing in the local minima on the wrong side of search space.
Been tinkering with pipecat.ai lately. Such a well designed framework to work with.
Trying to build multimodal context aware assistant one can self-host. 🤖
#pipecat #conversationalai #multimodal
Trying to build multimodal context aware assistant one can self-host. 🤖
#pipecat #conversationalai #multimodal
May 16, 2025 at 7:33 AM
Been tinkering with pipecat.ai lately. Such a well designed framework to work with.
Trying to build multimodal context aware assistant one can self-host. 🤖
#pipecat #conversationalai #multimodal
Trying to build multimodal context aware assistant one can self-host. 🤖
#pipecat #conversationalai #multimodal
Spent half day on inference script for image classifier. Is there a transformers-like pipeline for onnx models? I don’t want to install pytorch, so optimum won’t work here.
#huggingface #onnx #pytorch
#huggingface #onnx #pytorch
May 5, 2025 at 12:01 PM
Spent half day on inference script for image classifier. Is there a transformers-like pipeline for onnx models? I don’t want to install pytorch, so optimum won’t work here.
#huggingface #onnx #pytorch
#huggingface #onnx #pytorch
Having kids is obviously amazing. Don’t you love how your newborn wakes up the moment it touches the mattress after fifth round of you soothing it to sleep?
January 25, 2025 at 9:09 PM
Having kids is obviously amazing. Don’t you love how your newborn wakes up the moment it touches the mattress after fifth round of you soothing it to sleep?
Reposted by Juraj
LLMs are actually stateless. You put in the historic context as input.
Chat is only a UI constraint to build this context iteratively.
Chat is only a UI constraint to build this context iteratively.
January 4, 2025 at 8:53 PM
LLMs are actually stateless. You put in the historic context as input.
Chat is only a UI constraint to build this context iteratively.
Chat is only a UI constraint to build this context iteratively.
Today is my last day at company I’ve worked for two years. Learned a lot, met some great people.
Now, I’m ready to start new year with new challenges and am generally excited about how 2025 will turn out. 🙂
Fingers crossed 🤞.
Now, I’m ready to start new year with new challenges and am generally excited about how 2025 will turn out. 🙂
Fingers crossed 🤞.
December 31, 2024 at 4:34 PM
Today is my last day at company I’ve worked for two years. Learned a lot, met some great people.
Now, I’m ready to start new year with new challenges and am generally excited about how 2025 will turn out. 🙂
Fingers crossed 🤞.
Now, I’m ready to start new year with new challenges and am generally excited about how 2025 will turn out. 🙂
Fingers crossed 🤞.
Reposted by Juraj
This will never get old 🤣
December 31, 2024 at 12:06 PM
This will never get old 🤣
I’ve been exploring pocketbase.io for several weeks now and am quite impressed by it.
Today I’ve extended it with custom JS proxy routes to “hide” other APIs behind its auth.
What a nice tool to have in a tool belt! 🛠️
#webdev #api #backend
Today I’ve extended it with custom JS proxy routes to “hide” other APIs behind its auth.
What a nice tool to have in a tool belt! 🛠️
#webdev #api #backend
PocketBase - Open Source backend in 1 file
Open Source backend in 1 file with realtime database, authentication, file storage and admin dashboard
pocketbase.io
December 28, 2024 at 10:21 PM
I’ve been exploring pocketbase.io for several weeks now and am quite impressed by it.
Today I’ve extended it with custom JS proxy routes to “hide” other APIs behind its auth.
What a nice tool to have in a tool belt! 🛠️
#webdev #api #backend
Today I’ve extended it with custom JS proxy routes to “hide” other APIs behind its auth.
What a nice tool to have in a tool belt! 🛠️
#webdev #api #backend
Anyone got adaptive batching API for PIL images working with BentoML? The official docs example doesn’t work.
docs.bentoml.com/en/latest/bu...
#AI #ML
docs.bentoml.com/en/latest/bu...
#AI #ML
Define input and output types
When creating a BentoML Service, you need to specify the input and output (IO) types the Service’s API. These types are integral in shaping the logic of the Service API, guiding the flow of data in...
docs.bentoml.com
December 28, 2024 at 2:23 PM
Anyone got adaptive batching API for PIL images working with BentoML? The official docs example doesn’t work.
docs.bentoml.com/en/latest/bu...
#AI #ML
docs.bentoml.com/en/latest/bu...
#AI #ML
Reposted by Juraj
I'll get straight to the point.
We trained 2 new models. Like BERT, but modern. ModernBERT.
Not some hypey GenAI thing, but a proper workhorse model, for retrieval, classification, etc. Real practical stuff.
It's much faster, more accurate, longer context, and more useful. 🧵
We trained 2 new models. Like BERT, but modern. ModernBERT.
Not some hypey GenAI thing, but a proper workhorse model, for retrieval, classification, etc. Real practical stuff.
It's much faster, more accurate, longer context, and more useful. 🧵
December 19, 2024 at 4:45 PM
I'll get straight to the point.
We trained 2 new models. Like BERT, but modern. ModernBERT.
Not some hypey GenAI thing, but a proper workhorse model, for retrieval, classification, etc. Real practical stuff.
It's much faster, more accurate, longer context, and more useful. 🧵
We trained 2 new models. Like BERT, but modern. ModernBERT.
Not some hypey GenAI thing, but a proper workhorse model, for retrieval, classification, etc. Real practical stuff.
It's much faster, more accurate, longer context, and more useful. 🧵
Reposted by Juraj
Reposted by Juraj
On Linux you're an admin
On Mac you're an end user
On Windows you're a victim
On Mac you're an end user
On Windows you're a victim
December 14, 2024 at 12:26 AM
On Linux you're an admin
On Mac you're an end user
On Windows you're a victim
On Mac you're an end user
On Windows you're a victim
Reposted by Juraj
If you find yourself with too much free time over the (long) weekend / holidays, I have ~3h Building an LLM from the Ground Up workshop on YouTube that may come in handy: m.youtube.com/watch?v=quh7...
Building LLMs from the Ground Up: A 3-hour Coding Workshop
YouTube video by Sebastian Raschka
m.youtube.com
November 27, 2024 at 4:39 AM
If you find yourself with too much free time over the (long) weekend / holidays, I have ~3h Building an LLM from the Ground Up workshop on YouTube that may come in handy: m.youtube.com/watch?v=quh7...
Reposted by Juraj
Anthropic released an interesting thing today: an attempt at a standard protocol for LLM tools to talk to services that provide tools and extra context to be used other the models modelcontextprotocol.io
Introduction - Model Context Protocol
Get started with the Model Context Protocol (MCP)
modelcontextprotocol.io
November 25, 2024 at 4:37 PM
Anthropic released an interesting thing today: an attempt at a standard protocol for LLM tools to talk to services that provide tools and extra context to be used other the models modelcontextprotocol.io
Reposted by Juraj
I like this new analogy for working with LLMs by @emollick.bsky.social
"treat AI like an infinitely patient new coworker who forgets everything you tell them each new conversation, one that comes highly recommended but whose actual abilities are not that clear"
www.oneusefulthing.org/p/getting-st...
"treat AI like an infinitely patient new coworker who forgets everything you tell them each new conversation, one that comes highly recommended but whose actual abilities are not that clear"
www.oneusefulthing.org/p/getting-st...
Getting started with AI: Good enough prompting
Don't make this hard
www.oneusefulthing.org
November 25, 2024 at 6:16 AM
I like this new analogy for working with LLMs by @emollick.bsky.social
"treat AI like an infinitely patient new coworker who forgets everything you tell them each new conversation, one that comes highly recommended but whose actual abilities are not that clear"
www.oneusefulthing.org/p/getting-st...
"treat AI like an infinitely patient new coworker who forgets everything you tell them each new conversation, one that comes highly recommended but whose actual abilities are not that clear"
www.oneusefulthing.org/p/getting-st...
Few network resources disappeared from resource group on Azure. No logs or traces. Spent hour on call with support, no clue what happened.
Now my VM is just sitting there, bricked, floating in digital space, waiting for rescue. ☁️
Just another Monday.
Now my VM is just sitting there, bricked, floating in digital space, waiting for rescue. ☁️
Just another Monday.
November 18, 2024 at 9:57 AM
Few network resources disappeared from resource group on Azure. No logs or traces. Spent hour on call with support, no clue what happened.
Now my VM is just sitting there, bricked, floating in digital space, waiting for rescue. ☁️
Just another Monday.
Now my VM is just sitting there, bricked, floating in digital space, waiting for rescue. ☁️
Just another Monday.
Reposted by Juraj
Major AI Large Language Models (LLMs) ranked by capabilities (MMLU)
interactive https://informationisbeautiful.net/visualizations/the-rise-of-generative-ai-large-language-models-llms-like-chatgpt/
interactive https://informationisbeautiful.net/visualizations/the-rise-of-generative-ai-large-language-models-llms-like-chatgpt/
November 6, 2024 at 3:55 PM
Major AI Large Language Models (LLMs) ranked by capabilities (MMLU)
interactive https://informationisbeautiful.net/visualizations/the-rise-of-generative-ai-large-language-models-llms-like-chatgpt/
interactive https://informationisbeautiful.net/visualizations/the-rise-of-generative-ai-large-language-models-llms-like-chatgpt/
👋 Hello BlueSky! Another member just landed.
November 17, 2024 at 11:11 AM
👋 Hello BlueSky! Another member just landed.