Peter Sergeant
@sgnt.ai
Full-time building LLM and ML powered NPCs/agents for a popular online game. pete@sgnt.ai
Forget the complexity: AI all boils down to drawing the right lines: sgnt.ai/p/finding-li...
Forget the complexity: AI all boils down to drawing the right lines | sgnt.ai
Over and over again, despite the best efforts of humans, the most effective AI systems come down to one simple idea: finding the right shaped line that fits some data points.
sgnt.ai
August 2, 2025 at 6:28 AM
Forget the complexity: AI all boils down to drawing the right lines: sgnt.ai/p/finding-li...
In RAG, your chunks solve three distinct problems; trying to use one algorithm to solve all three probably isn't optimal: sgnt.ai/p/rag-trinity/
July 8, 2025 at 9:22 AM
In RAG, your chunks solve three distinct problems; trying to use one algorithm to solve all three probably isn't optimal: sgnt.ai/p/rag-trinity/
One day in 2012 I wrote up from a nightmare in which I was being chased by angle brackets, and sweating profusely, and found this code in my editor github.com/pjlsergeant/...
GitHub - pjlsergeant/xslt-fever-dream: XSLT is a great programming language
XSLT is a great programming language. Contribute to pjlsergeant/xslt-fever-dream development by creating an account on GitHub.
github.com
June 30, 2025 at 9:10 AM
One day in 2012 I wrote up from a nightmare in which I was being chased by angle brackets, and sweating profusely, and found this code in my editor github.com/pjlsergeant/...
I will fix your vibe-coded MVP. Not joking. sgnt.ai/p/vibe-coded/
I will fix your vibe-coded MVP | sgnt.ai
You delivered your vision quickly using one of the many excellent LLM-based coding tools, users are happy. I will dig you out of the tech-debt hole you have created.
sgnt.ai
June 28, 2025 at 7:29 AM
I will fix your vibe-coded MVP. Not joking. sgnt.ai/p/vibe-coded/
China sends its most promising civil servants to a US university for 1-3 years, and rather seeing this as a total and complete Cultural Victory, recruitment opportunity, and chance to indoctrinate them, the Trump administration wants to shut this down. Baffling. www.wsj.com/world/china/...
Harvard Has Trained So Many Chinese Communist Officials, They Call It Their ‘Party School’
The university’s Kennedy School of Government has long been favored by party cadres seeking career boosts.
www.wsj.com
June 2, 2025 at 5:54 AM
China sends its most promising civil servants to a US university for 1-3 years, and rather seeing this as a total and complete Cultural Victory, recruitment opportunity, and chance to indoctrinate them, the Trump administration wants to shut this down. Baffling. www.wsj.com/world/china/...
Three dumb ChatGPT tricks I use all the time...
1. If I need work critiqued, I tell the LLM that I got someone else to write it for me, and I'm going to pay them based on how good it is. Less time spent softening feedback, and more time spent on pros and cons. Repeat we get to a solid 9 or 10/10
1. If I need work critiqued, I tell the LLM that I got someone else to write it for me, and I'm going to pay them based on how good it is. Less time spent softening feedback, and more time spent on pros and cons. Repeat we get to a solid 9 or 10/10
May 22, 2025 at 5:28 PM
Three dumb ChatGPT tricks I use all the time...
1. If I need work critiqued, I tell the LLM that I got someone else to write it for me, and I'm going to pay them based on how good it is. Less time spent softening feedback, and more time spent on pros and cons. Repeat we get to a solid 9 or 10/10
1. If I need work critiqued, I tell the LLM that I got someone else to write it for me, and I'm going to pay them based on how good it is. Less time spent softening feedback, and more time spent on pros and cons. Repeat we get to a solid 9 or 10/10
I finally completed an article I've been trying to write for a year; the non-programmer's guide to embeddings! No maths, lots of dogs, and a step by step intuitive guide: sgnt.ai/p/embeddings...
Understanding Modern AI is Understanding Embeddings: A Guide for Non-Programmers (with lots of dogs!) | sgnt.ai
Embeddings are a core AI concept that underpin a great deal of what we today think of as being AI. This article is going to give you an accurate and intuitive understanding of what an “embedding” is i...
sgnt.ai
May 8, 2025 at 9:36 AM
I finally completed an article I've been trying to write for a year; the non-programmer's guide to embeddings! No maths, lots of dogs, and a step by step intuitive guide: sgnt.ai/p/embeddings...
Reposted by Peter Sergeant
It's final paper season.
May 5, 2025 at 9:55 PM
It's final paper season.
Let’s say we were to discover tomorrow that dolphins are in fact fish, not mammals. Given the huge amount of data in LLM training sets asserting that dolphins are mammals, how does that fact end up getting updated? Just that we generate more new text as time goes on and we eventually have more …
May 3, 2025 at 5:44 AM
Let’s say we were to discover tomorrow that dolphins are in fact fish, not mammals. Given the huge amount of data in LLM training sets asserting that dolphins are mammals, how does that fact end up getting updated? Just that we generate more new text as time goes on and we eventually have more …
Our LLM game NPC couldn't block chat input & got interrupted constantly ... we engineered "killable" responses using cancel tokens + input debouncing so it could pivot instantly like a human. Made interactions way more natural for impatient players. sgnt.ai/p/interrupti...
When Users Won’t Wait: Engineering Killable LLM Responses | sgnt.ai
In our application, the chatbot can’t hide behind a loading spinner; users keep talking and expect it to pivot instantly. This constraint forced us to develop some lightweight techniques you can graft...
sgnt.ai
April 22, 2025 at 4:53 AM
Our LLM game NPC couldn't block chat input & got interrupted constantly ... we engineered "killable" responses using cancel tokens + input debouncing so it could pivot instantly like a human. Made interactions way more natural for impatient players. sgnt.ai/p/interrupti...
In-memory free-text search is a super-power for LLMs; spend less on inference by sprinkling in some free lexical search into the prompt… sgnt.ai/p/free-text-...
In-memory free-text search is a super-power for LLMs | sgnt.ai
While working on LLM-driven NPCs, I observed significant improvements in several areas by adding a simple component: in-memory free-text search
sgnt.ai
April 19, 2025 at 9:28 AM
In-memory free-text search is a super-power for LLMs; spend less on inference by sprinkling in some free lexical search into the prompt… sgnt.ai/p/free-text-...
From OpenAI’s agent building advice. The first two of these are terrible, terrible ideas for things to give to a LLM to make a decision on. More: sgnt.ai/p/hell-out-o...
April 18, 2025 at 2:29 AM
From OpenAI’s agent building advice. The first two of these are terrible, terrible ideas for things to give to a LLM to make a decision on. More: sgnt.ai/p/hell-out-o...
I would love to see more research about whatever we’re calling Sapir-Whorf for LLMs. Do you get substantially different opinions from an LLM depending on which language you query it in? Does its opinion on the greatest empire of all time change depending on if your query is Mongolian or Italian?
April 15, 2025 at 3:02 PM
I would love to see more research about whatever we’re calling Sapir-Whorf for LLMs. Do you get substantially different opinions from an LLM depending on which language you query it in? Does its opinion on the greatest empire of all time change depending on if your query is Mongolian or Italian?
Don't let an LLM make decisions or implement business logic, they suck at that: sgnt.ai/p/hell-out-o...
April 1, 2025 at 2:35 AM
Don't let an LLM make decisions or implement business logic, they suck at that: sgnt.ai/p/hell-out-o...
Four bad definitions of agentic AI: sgnt.ai/p/agentic-ai...
Four bad definitions of "Agentic AI" | sgnt.ai
If your team promises to deliver (or buy!) 'Agentic AI', then everyone needs to have a shared understanding of what that means; you don't want to be the one left trying to explain the mismatch to stak...
sgnt.ai
March 30, 2025 at 10:48 AM
Four bad definitions of agentic AI: sgnt.ai/p/agentic-ai...
Is anyone else building behavioural plugins for agents / chat-bots? Certain modes can be enabled for brief periods that add new functionality depending on triggers? I keep having to invent novel stuff for this project, and it would be amazing to chat to people doing anything vaguely similar
March 28, 2025 at 10:41 AM
Is anyone else building behavioural plugins for agents / chat-bots? Certain modes can be enabled for brief periods that add new functionality depending on triggers? I keep having to invent novel stuff for this project, and it would be amazing to chat to people doing anything vaguely similar
Remake of Eternal Sunshine of the Spotless Mind, only this time the guy’s seducing her based on her ChatGPT history
March 9, 2025 at 5:08 AM
Remake of Eternal Sunshine of the Spotless Mind, only this time the guy’s seducing her based on her ChatGPT history
Please can we not radicalize Mark Cuban by being mean to him online
I'm dumb. I can't figure out how to end world hunger. But I do promise that I will continue to change healthcare in this country and make it more affordable, possibly setting a path towards Universal Healthcare.
February 23, 2025 at 6:57 AM
Please can we not radicalize Mark Cuban by being mean to him online
If they've RLHF'd out the ability for ChatGPT to check its own working I'm gonna be pissed
February 19, 2025 at 3:21 AM
If they've RLHF'd out the ability for ChatGPT to check its own working I'm gonna be pissed
I’m not going to link to the article because we don’t reward clickbait in this house, but claiming that “generative AI is a con” because OpenAI and Anthropic haven’t proven that prop-model plus selling inference is a good business model is dumb
February 18, 2025 at 11:50 AM
I’m not going to link to the article because we don’t reward clickbait in this house, but claiming that “generative AI is a con” because OpenAI and Anthropic haven’t proven that prop-model plus selling inference is a good business model is dumb
Full marks for self-confidence but _nil points_ for execution there buddy
February 8, 2025 at 6:10 AM
Full marks for self-confidence but _nil points_ for execution there buddy
I’m aware of two reasonably good definitions of Agentic AI, but I can definitively tell you that in practice it just means “stuff that AI might be able to do for us some day”. I haven’t heard anyone use it as anything other as a stand-in for “awesome stuff coming soon” in 3 days of this expo
February 6, 2025 at 10:18 AM
I’m aware of two reasonably good definitions of Agentic AI, but I can definitively tell you that in practice it just means “stuff that AI might be able to do for us some day”. I haven’t heard anyone use it as anything other as a stand-in for “awesome stuff coming soon” in 3 days of this expo
I’ve done a few decades of software engineering and never had to deal with a field before where keeping the ability to rip out components is such an advantage as AI
February 6, 2025 at 9:06 AM
I’ve done a few decades of software engineering and never had to deal with a field before where keeping the ability to rip out components is such an advantage as AI
At an AI expo in Dubai. Nothing destroys an exhibitor’s credibility faster than having the word blockchain anywhere near their product
February 6, 2025 at 9:05 AM
At an AI expo in Dubai. Nothing destroys an exhibitor’s credibility faster than having the word blockchain anywhere near their product