Olatomiwa Bifarin
@bifarinthefifth.bsky.social
essayist @ http://youtube.com/@epistemeEngine
AI blog @ http://theepsilon.substack.com
μgrants @ https://mbbgrant.substack.com
AI blog @ http://theepsilon.substack.com
μgrants @ https://mbbgrant.substack.com
A couple days ago, I attended the IBM Tech Exchange Dev Day at Georgia Tech on Open Source AI.
I ended up learning more than I thought I would. From Docling to Generative Computing, my notes:
theepsilon.substack.com/p/from-gran...
I ended up learning more than I thought I would. From Docling to Generative Computing, my notes:
theepsilon.substack.com/p/from-gran...
From Granite to Generative Computing
IBM’s Foundational Models, Unstructured Document Processing, and Generative Computing.
theepsilon.substack.com
August 23, 2025 at 6:53 PM
A couple days ago, I attended the IBM Tech Exchange Dev Day at Georgia Tech on Open Source AI.
I ended up learning more than I thought I would. From Docling to Generative Computing, my notes:
theepsilon.substack.com/p/from-gran...
I ended up learning more than I thought I would. From Docling to Generative Computing, my notes:
theepsilon.substack.com/p/from-gran...
The latest pulse, Issue 28:
GPT-5👨🏿💻, Comet🌐, and How to Publish for Machines📄
theepsilon.substack.com/p/pulse-iss...
GPT-5👨🏿💻, Comet🌐, and How to Publish for Machines📄
theepsilon.substack.com/p/pulse-iss...
August 16, 2025 at 6:04 PM
The latest pulse, Issue 28:
GPT-5👨🏿💻, Comet🌐, and How to Publish for Machines📄
theepsilon.substack.com/p/pulse-iss...
GPT-5👨🏿💻, Comet🌐, and How to Publish for Machines📄
theepsilon.substack.com/p/pulse-iss...
It's already clear that knowledge works are going to undergo a massive restructuring (to say the least) over the next decade; many (most notably in coding) are already well under way.
And knowledge work does not preclude running a lab & doing science.
And knowledge work does not preclude running a lab & doing science.
July 19, 2025 at 2:10 PM
It's already clear that knowledge works are going to undergo a massive restructuring (to say the least) over the next decade; many (most notably in coding) are already well under way.
And knowledge work does not preclude running a lab & doing science.
And knowledge work does not preclude running a lab & doing science.
My latest AI reading list
ε Pulse: Issue 27 -> Context Engineering👷🏿, Grok 4📒, and a Foundation Model for Tumor Microenvironment 🎗
theepsilon.substack.com/p/pulse-iss...
ε Pulse: Issue 27 -> Context Engineering👷🏿, Grok 4📒, and a Foundation Model for Tumor Microenvironment 🎗
theepsilon.substack.com/p/pulse-iss...
July 12, 2025 at 1:44 PM
My latest AI reading list
ε Pulse: Issue 27 -> Context Engineering👷🏿, Grok 4📒, and a Foundation Model for Tumor Microenvironment 🎗
theepsilon.substack.com/p/pulse-iss...
ε Pulse: Issue 27 -> Context Engineering👷🏿, Grok 4📒, and a Foundation Model for Tumor Microenvironment 🎗
theepsilon.substack.com/p/pulse-iss...
What happens when an AI runs a business?
Anthropic put Claude in charge of a real-world vending machine for their "Project Vend" experiment.
Anthropic put Claude in charge of a real-world vending machine for their "Project Vend" experiment.
July 10, 2025 at 6:53 PM
What happens when an AI runs a business?
Anthropic put Claude in charge of a real-world vending machine for their "Project Vend" experiment.
Anthropic put Claude in charge of a real-world vending machine for their "Project Vend" experiment.
Folks at Cognition argues against building multi-agent AI systems.
The author argues that decomposing tasks for multiple agents creates more problems (like context sharing) than it solves.
More here: cognition.ai/blog/dont-b...
The author argues that decomposing tasks for multiple agents creates more problems (like context sharing) than it solves.
More here: cognition.ai/blog/dont-b...
July 7, 2025 at 9:11 PM
Folks at Cognition argues against building multi-agent AI systems.
The author argues that decomposing tasks for multiple agents creates more problems (like context sharing) than it solves.
More here: cognition.ai/blog/dont-b...
The author argues that decomposing tasks for multiple agents creates more problems (like context sharing) than it solves.
More here: cognition.ai/blog/dont-b...
Anthropic engineers' take on building multi-agent research system to tackle complex, open-ended questions.
A lead agent delegates tasks to sub-agents who research in parallel in an orchestrator-worker agentic pattern
A lead agent delegates tasks to sub-agents who research in parallel in an orchestrator-worker agentic pattern
July 5, 2025 at 9:15 PM
Anthropic engineers' take on building multi-agent research system to tackle complex, open-ended questions.
A lead agent delegates tasks to sub-agents who research in parallel in an orchestrator-worker agentic pattern
A lead agent delegates tasks to sub-agents who research in parallel in an orchestrator-worker agentic pattern
Fine essay here on Bio-ML and Noetik (a startup building foundation models of tumor microenvironment)
The thesis: The future of bio-ML is using rich, multimodal data to build foundation models for complex diseases, rather than focusing on simpler problems.
www.owlposting.com/p/joining-n...
The thesis: The future of bio-ML is using rich, multimodal data to build foundation models for complex diseases, rather than focusing on simpler problems.
www.owlposting.com/p/joining-n...
July 4, 2025 at 1:39 PM
Fine essay here on Bio-ML and Noetik (a startup building foundation models of tumor microenvironment)
The thesis: The future of bio-ML is using rich, multimodal data to build foundation models for complex diseases, rather than focusing on simpler problems.
www.owlposting.com/p/joining-n...
The thesis: The future of bio-ML is using rich, multimodal data to build foundation models for complex diseases, rather than focusing on simpler problems.
www.owlposting.com/p/joining-n...
My latest academic work on applied NLP is now published in Analytical Chemistry:
"A Large Language Model–Powered Map of Metabolomics Research"
Paper: pubs.acs.org/doi/10.1021...
App: metascape.streamlit.app/
"A Large Language Model–Powered Map of Metabolomics Research"
Paper: pubs.acs.org/doi/10.1021...
App: metascape.streamlit.app/
July 3, 2025 at 9:49 PM
My latest academic work on applied NLP is now published in Analytical Chemistry:
"A Large Language Model–Powered Map of Metabolomics Research"
Paper: pubs.acs.org/doi/10.1021...
App: metascape.streamlit.app/
"A Large Language Model–Powered Map of Metabolomics Research"
Paper: pubs.acs.org/doi/10.1021...
App: metascape.streamlit.app/
my notes on topic coherence measures in NLP, over at my AI blog.
theepsilon.substack.com/p/topic-coh...
theepsilon.substack.com/p/topic-coh...
Topic Coherence Metrics for Dummies
A non-technical treatment of topic model evaluation
theepsilon.substack.com
June 28, 2025 at 7:57 PM
my notes on topic coherence measures in NLP, over at my AI blog.
theepsilon.substack.com/p/topic-coh...
theepsilon.substack.com/p/topic-coh...
Andrej's analogy game is a hard.
I really enjoyed listening to his talk on software in the age of AI. Highly recommend, if you haven't watched it already.
www.youtube.com/watch?v=LCE...
I really enjoyed listening to his talk on software in the age of AI. Highly recommend, if you haven't watched it already.
www.youtube.com/watch?v=LCE...
June 27, 2025 at 10:19 PM
Andrej's analogy game is a hard.
I really enjoyed listening to his talk on software in the age of AI. Highly recommend, if you haven't watched it already.
www.youtube.com/watch?v=LCE...
I really enjoyed listening to his talk on software in the age of AI. Highly recommend, if you haven't watched it already.
www.youtube.com/watch?v=LCE...
We traded calloused hands for blue-light screens, thinking knowledge work would end human suffering. It eased plenty no doubt; yet we swapped worn-out bodies for sedentary-induced metabolic ‘fallouts’ (obesity, diabetes, and the like.), and all the suffering downstream. Progress with a hidden bill.
June 26, 2025 at 10:00 PM
We traded calloused hands for blue-light screens, thinking knowledge work would end human suffering. It eased plenty no doubt; yet we swapped worn-out bodies for sedentary-induced metabolic ‘fallouts’ (obesity, diabetes, and the like.), and all the suffering downstream. Progress with a hidden bill.
I came across this nice talk the other day: www.youtube.com/watch?v=uFP...
Building effective agents with mcp via an agent library "mcp-agent"
Building effective agents with mcp via an agent library "mcp-agent"
June 24, 2025 at 9:28 PM
I came across this nice talk the other day: www.youtube.com/watch?v=uFP...
Building effective agents with mcp via an agent library "mcp-agent"
Building effective agents with mcp via an agent library "mcp-agent"
June 23, 2025 at 11:47 PM
This is a good (video) podcast on Mech Interp, highlighting recent publications from Anthropic: www.youtube.com/watch?v=9YQ...
Their research aims to move beyond treating LLMs as black boxes and instead reveal their "intermediate thought processes" via attribution graphs.
Their research aims to move beyond treating LLMs as black boxes and instead reveal their "intermediate thought processes" via attribution graphs.
June 21, 2025 at 10:42 PM
This is a good (video) podcast on Mech Interp, highlighting recent publications from Anthropic: www.youtube.com/watch?v=9YQ...
Their research aims to move beyond treating LLMs as black boxes and instead reveal their "intermediate thought processes" via attribution graphs.
Their research aims to move beyond treating LLMs as black boxes and instead reveal their "intermediate thought processes" via attribution graphs.
What I am reading this summer:
www.epistemeengine.com/p/what-i-am...
www.epistemeengine.com/p/what-i-am...
June 21, 2025 at 7:35 PM
What I am reading this summer:
www.epistemeengine.com/p/what-i-am...
www.epistemeengine.com/p/what-i-am...
Sam Altman on the "Gentle Singularity": blog.samaltman.com/the-gentle-...
June 20, 2025 at 9:34 PM
Sam Altman on the "Gentle Singularity": blog.samaltman.com/the-gentle-...
Which startup are your investing in?
Cogito, The Prince, Form Room, Proletariat Perks, or Sisyphus
Cogito, The Prince, Form Room, Proletariat Perks, or Sisyphus
June 19, 2025 at 11:44 PM
Which startup are your investing in?
Cogito, The Prince, Form Room, Proletariat Perks, or Sisyphus
Cogito, The Prince, Form Room, Proletariat Perks, or Sisyphus
The other day, I used a prompt to write a prompt that then writes another prompt.
I suppose you can just do stuff these days.
I suppose you can just do stuff these days.
June 18, 2025 at 9:59 PM
The other day, I used a prompt to write a prompt that then writes another prompt.
I suppose you can just do stuff these days.
I suppose you can just do stuff these days.
It takes some time for it to sink in but properly viewed, productivity isn’t about doing more; it’s about ignoring nearly everything, and that precisely, is what makes it incredibly hard.
June 16, 2025 at 9:57 PM
It takes some time for it to sink in but properly viewed, productivity isn’t about doing more; it’s about ignoring nearly everything, and that precisely, is what makes it incredibly hard.
June 10, 2025 at 11:18 PM
June 9, 2025 at 11:30 PM
Powerful action space, decentralization, privacy & security.
A clear-eyed argument for personal, local, private AI agents by
soumith chintala
www.youtube.com/watch?v=jMo...
A clear-eyed argument for personal, local, private AI agents by
soumith chintala
www.youtube.com/watch?v=jMo...
Personal, Local, Private AI Agents: Soumith Chintala
AI Agents are being worked upon by lots of people. But can they run locally, fast, keep your information access in your control and help you trust them with ...
www.youtube.com
June 6, 2025 at 10:18 AM
Powerful action space, decentralization, privacy & security.
A clear-eyed argument for personal, local, private AI agents by
soumith chintala
www.youtube.com/watch?v=jMo...
A clear-eyed argument for personal, local, private AI agents by
soumith chintala
www.youtube.com/watch?v=jMo...