Mark Torres
@markptorres.bsky.social
ML Eng @Northwestern, building recommender algos and LLM apps. Building Bluesky feeds @ https://bsky.app/profile/mindtechnologylab.bsky.social. BS (Statistics) @Yale + MS (Computer Science) @UT Austin. Recovering startup tech bro.
Claude 4 is the first LLM that has allowed me to actually "vibe code" a decently complicated app in Cursor purely through instructions and markdown files and without having to write a single line of code. Had to intervene a few times in the chat but otherwise really impressive!
May 25, 2025 at 7:04 PM
Claude 4 is the first LLM that has allowed me to actually "vibe code" a decently complicated app in Cursor purely through instructions and markdown files and without having to write a single line of code. Had to intervene a few times in the chat but otherwise really impressive!
I can't believe that in 2025, we can run reasoning models locally. I finally got to try Ollama and QwQ and it's really impressive. Next step is to set up Ollama + Cursor. Can't imagine where things will be in 2026 and beyond.
ollama.com/library/qwq
mem.ai/p/bf6ew6HSm1...
ollama.com/library/qwq
mem.ai/p/bf6ew6HSm1...
qwq
QwQ is the reasoning model of the Qwen series.
ollama.com
March 16, 2025 at 4:40 AM
I can't believe that in 2025, we can run reasoning models locally. I finally got to try Ollama and QwQ and it's really impressive. Next step is to set up Ollama + Cursor. Can't imagine where things will be in 2026 and beyond.
ollama.com/library/qwq
mem.ai/p/bf6ew6HSm1...
ollama.com/library/qwq
mem.ai/p/bf6ew6HSm1...
I still think people should step back sometimes and just think about how far AI has come in the past 5 years. NLP used to be "fine-tune BERT and hope it works" to "do one-shot inference, on any task, using GPT 4o-mini". Can't take it for granted that SOTA AI is an API call away...
January 31, 2025 at 11:16 PM
I still think people should step back sometimes and just think about how far AI has come in the past 5 years. NLP used to be "fine-tune BERT and hope it works" to "do one-shot inference, on any task, using GPT 4o-mini". Can't take it for granted that SOTA AI is an API call away...
The reasoning trace of OpenAI's o3-mini seems like them trying to strike a balance between "we want to keep our reasoning traces IP" and "we want people to think we're being transparent". Still definitely prefer the depth of DeepSeek's traces, though it's still too early to tell.
January 31, 2025 at 11:12 PM
The reasoning trace of OpenAI's o3-mini seems like them trying to strike a balance between "we want to keep our reasoning traces IP" and "we want people to think we're being transparent". Still definitely prefer the depth of DeepSeek's traces, though it's still too early to tell.
I just read Stolen Focus and I really recommend it to anyone interested in a holistic systems overview of why it’s so hard to keep your attention on anything.
Who could’ve guessed that the key for success is eating healthy, drinking water, sleeping 7-8 hours, exercising, and reading books 🤣
Who could’ve guessed that the key for success is eating healthy, drinking water, sleeping 7-8 hours, exercising, and reading books 🤣
Stolen Focus: Why You Can't Pay Attention— and How to T…
Our ability to pay attention is collapsing. From the Ne…
www.goodreads.com
January 17, 2025 at 12:49 AM
I just read Stolen Focus and I really recommend it to anyone interested in a holistic systems overview of why it’s so hard to keep your attention on anything.
Who could’ve guessed that the key for success is eating healthy, drinking water, sleeping 7-8 hours, exercising, and reading books 🤣
Who could’ve guessed that the key for success is eating healthy, drinking water, sleeping 7-8 hours, exercising, and reading books 🤣
Heard this zinger take at a talk:
“Most lay people shouldn’t read scientific papers, even if they think they can, because most people don’t understand that science is an iterative process. There’s no “right answer”, and people do disagree. Even laws are just ideas that we haven’t proven wrong yet.”
“Most lay people shouldn’t read scientific papers, even if they think they can, because most people don’t understand that science is an iterative process. There’s no “right answer”, and people do disagree. Even laws are just ideas that we haven’t proven wrong yet.”
January 17, 2025 at 12:42 AM
Heard this zinger take at a talk:
“Most lay people shouldn’t read scientific papers, even if they think they can, because most people don’t understand that science is an iterative process. There’s no “right answer”, and people do disagree. Even laws are just ideas that we haven’t proven wrong yet.”
“Most lay people shouldn’t read scientific papers, even if they think they can, because most people don’t understand that science is an iterative process. There’s no “right answer”, and people do disagree. Even laws are just ideas that we haven’t proven wrong yet.”
Reposted by Mark Torres
NEW: Meta has quietly dismantled the system that prevented misinformation from spreading in the United States. Machine-learning classifiers that once identified viral hoaxes and limited their reach have now been switched off, Platformer has learned www.platformer.news/meta-ends-mi...
January 15, 2025 at 12:51 AM
NEW: Meta has quietly dismantled the system that prevented misinformation from spreading in the United States. Machine-learning classifiers that once identified viral hoaxes and limited their reach have now been switched off, Platformer has learned www.platformer.news/meta-ends-mi...
I've been experimenting with NotebookLM to read papers in podcast form and it's been great at it! If I add more than 1-2 papers though, I find that the quality suffers. Plus it caps out at ~20 minutes, can ramble, and its adherence to system prompts is iffy. Great tool though!
Google NotebookLM | Note Taking & Research Assistant Powered by AI
Use the power of AI for quick summarization and note taking, NotebookLM is your powerful virtual research assistant rooted in information you can trust.
notebooklm.google
January 5, 2025 at 9:33 PM
I've been experimenting with NotebookLM to read papers in podcast form and it's been great at it! If I add more than 1-2 papers though, I find that the quality suffers. Plus it caps out at ~20 minutes, can ramble, and its adherence to system prompts is iffy. Great tool though!
I wonder if filtering spam in the age of LLMs is similar to designing good CAPTCHAs now, where it's hard to create a filter that catches the best LLMs but is also easy enough for the average person. Especially true since it's hard to reliably tell LLM-generated text from human text.
December 10, 2024 at 9:12 PM
I wonder if filtering spam in the age of LLMs is similar to designing good CAPTCHAs now, where it's hard to create a filter that catches the best LLMs but is also easy enough for the average person. Especially true since it's hard to reliably tell LLM-generated text from human text.
Reposted by Mark Torres
another test post
December 10, 2024 at 12:13 AM
another test post
Reposted by Mark Torres
Reposted by Mark Torres
Oh wow, LG just released their own open source* LLM. If their published benchmarks are accurate, the 32B model is at least on par with Qwen2.5 (which is already an incredibly strong model), if not better.
www.lgresearch.ai/blog/view?se...
huggingface.co/LGAI-EXAONE
* open weights
www.lgresearch.ai/blog/view?se...
huggingface.co/LGAI-EXAONE
* open weights
Open-sourcing Three EXAONE 3.5 Models : Frontier-level Model, Top-tier Performance in Instruction Following and Long Context Capabilities - LG AI Research BLOG
www.lgresearch.ai
December 9, 2024 at 5:10 AM
Oh wow, LG just released their own open source* LLM. If their published benchmarks are accurate, the 32B model is at least on par with Qwen2.5 (which is already an incredibly strong model), if not better.
www.lgresearch.ai/blog/view?se...
huggingface.co/LGAI-EXAONE
* open weights
www.lgresearch.ai/blog/view?se...
huggingface.co/LGAI-EXAONE
* open weights
another test post
December 10, 2024 at 12:13 AM
another test post
Reposted by Mark Torres
I'm not mad at a baseball player getting paid his money, but its wild to me that MLB has teams that can shell out over $700 million for a player and teams that apparently can't build a stadium without taxpayer money.
December 9, 2024 at 5:21 PM
I'm not mad at a baseball player getting paid his money, but its wild to me that MLB has teams that can shell out over $700 million for a player and teams that apparently can't build a stadium without taxpayer money.
I finally learned what Snowflake and Databricks actually do and I now question why I worked for 3 years building essentially an in-house, worse version of what someone with basic SQL knowledge could have done on Snowflake...
December 9, 2024 at 7:54 PM
I finally learned what Snowflake and Databricks actually do and I now question why I worked for 3 years building essentially an in-house, worse version of what someone with basic SQL knowledge could have done on Snowflake...
The news just came out about the arrest of the CEO's killer and Polymarket is wayyyyy too quick with releasing their latest betting odds 😂
December 9, 2024 at 7:42 PM
The news just came out about the arrest of the CEO's killer and Polymarket is wayyyyy too quick with releasing their latest betting odds 😂
Reposted by Mark Torres
reply to my own post!
August 3, 2024 at 12:34 AM
reply to my own post!
I've never liked tools that try to be "AI writing assistants", but I do like asking ChatGPT to analyze what I've written, give me detailed critique, and then give me line-by-line suggestions for how to improve clarity. Hard to make a tool though that works for everyone's style and use case.
December 2, 2024 at 1:10 AM
I've never liked tools that try to be "AI writing assistants", but I do like asking ChatGPT to analyze what I've written, give me detailed critique, and then give me line-by-line suggestions for how to improve clarity. Hard to make a tool though that works for everyone's style and use case.
Reposted by Mark Torres
It's been interesting to witness in real-time how the usage of "algorithm" in many places has shifted from a neutral "sequence of instructions" to a negative "controlled ordering and boosting of information".
November 30, 2024 at 10:26 AM
It's been interesting to witness in real-time how the usage of "algorithm" in many places has shifted from a neutral "sequence of instructions" to a negative "controlled ordering and boosting of information".
Reposted by Mark Torres
Whenever AI "generates" something impressive, the first question we should always ask is: "What does the closest sample in the training data look like?"
LLMs are amazing interfaces for accessing the world's information but they need to be treated as the "search and synthesis" tools they are.
LLMs are amazing interfaces for accessing the world's information but they need to be treated as the "search and synthesis" tools they are.
November 21, 2024 at 9:31 AM
Whenever AI "generates" something impressive, the first question we should always ask is: "What does the closest sample in the training data look like?"
LLMs are amazing interfaces for accessing the world's information but they need to be treated as the "search and synthesis" tools they are.
LLMs are amazing interfaces for accessing the world's information but they need to be treated as the "search and synthesis" tools they are.
The hardest part about AI agents is coming up with a spicy name. Very important! This is what Claude came up with.
Nexus
Prism
Cipher
Atlas
Nova
Quantum
Echo
Aegis
Zenith
Helios
We need an AI agent whose only job is coming up with good AI agent names and then grabbing the .ai domain for it.
Nexus
Prism
Cipher
Atlas
Nova
Quantum
Echo
Aegis
Zenith
Helios
We need an AI agent whose only job is coming up with good AI agent names and then grabbing the .ai domain for it.
November 30, 2024 at 2:01 AM
The hardest part about AI agents is coming up with a spicy name. Very important! This is what Claude came up with.
Nexus
Prism
Cipher
Atlas
Nova
Quantum
Echo
Aegis
Zenith
Helios
We need an AI agent whose only job is coming up with good AI agent names and then grabbing the .ai domain for it.
Nexus
Prism
Cipher
Atlas
Nova
Quantum
Echo
Aegis
Zenith
Helios
We need an AI agent whose only job is coming up with good AI agent names and then grabbing the .ai domain for it.
A lot of RAG content online is either (1) too academic and prescriptive or (2) is a basic toy example, so reading something like this is a nice reminder that "the best way to do something is the one that actually works", as obvious as it sounds.
Building a RAG system? There’s no one embedding model to rule them all
In this blog post, we'll explore a case study that demonstrates why popular heuristics like
www.pointable.ai
November 30, 2024 at 12:54 AM
A lot of RAG content online is either (1) too academic and prescriptive or (2) is a basic toy example, so reading something like this is a nice reminder that "the best way to do something is the one that actually works", as obvious as it sounds.