Peter Sergeant
@sgnt.ai
Full-time building LLM and ML powered NPCs/agents for a popular online game. pete@sgnt.ai
In sharp contrast to 90% of the comments here, I am absolutely not a fan, but you are bang on the money here. I am not hallucinating that my mother and wife use ChatGPT as their primary information source. I did not imagine many hours on specific tasks that LLMs have saved me.
August 9, 2025 at 7:34 AM
In sharp contrast to 90% of the comments here, I am absolutely not a fan, but you are bang on the money here. I am not hallucinating that my mother and wife use ChatGPT as their primary information source. I did not imagine many hours on specific tasks that LLMs have saved me.
Those drugs are the best thing to happen to me
August 6, 2025 at 3:48 PM
Those drugs are the best thing to happen to me
ChatGPT gave me what as far as I can tell is a genuinely novel idea for an algorithm (well, a novel application of a well-known algorithm) and now I’m having self doubts
July 30, 2025 at 4:46 AM
ChatGPT gave me what as far as I can tell is a genuinely novel idea for an algorithm (well, a novel application of a well-known algorithm) and now I’m having self doubts
I saw some guy saying they refuse to answer about “crime statistics” and chastise him for asking, which was a head-scratcher
July 30, 2025 at 4:18 AM
I saw some guy saying they refuse to answer about “crime statistics” and chastise him for asking, which was a head-scratcher
I think that’s prima facie not a workable approach in practice, but, criminal liability for directors and fines that make bond owners take a huge loss could work
July 28, 2025 at 2:10 PM
I think that’s prima facie not a workable approach in practice, but, criminal liability for directors and fines that make bond owners take a huge loss could work
The worst part is the dramatic medication changes often happen when you’re already not at your strongest so it can be hard to pick apart 🤷♂️
July 25, 2025 at 6:17 PM
The worst part is the dramatic medication changes often happen when you’re already not at your strongest so it can be hard to pick apart 🤷♂️
I ran a small boutique recruitment agency as a side project for a few years and it was highly fulfilling (people are so grateful on both sides, improving people’s lives), very lucrative (£100k a year), and really didn’t take that much work (1-2 hours a day). If you have the network, do it!
July 24, 2025 at 4:09 AM
I ran a small boutique recruitment agency as a side project for a few years and it was highly fulfilling (people are so grateful on both sides, improving people’s lives), very lucrative (£100k a year), and really didn’t take that much work (1-2 hours a day). If you have the network, do it!
The region is absolutely stuffed with US bases and detachments … with the notable exception of Israel www.aljazeera.com/amp/news/202...
Mapping US troops and military bases in the Middle East
There are between 40,000 and 50,000 US troops in the Middle East across at least 19 sites.
www.aljazeera.com
July 21, 2025 at 10:48 AM
The region is absolutely stuffed with US bases and detachments … with the notable exception of Israel www.aljazeera.com/amp/news/202...
I mean it’s theoretical because consumers can (usually) shop prices, whatever Delta’s exec fantasies might be
July 17, 2025 at 7:45 AM
I mean it’s theoretical because consumers can (usually) shop prices, whatever Delta’s exec fantasies might be
Spread the joy! 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
July 11, 2025 at 5:37 AM
Spread the joy! sgnt.ai/p/embeddings...
Proof of concept that you can get an LLM to disbelieve its own lying eyes
July 10, 2025 at 2:18 AM
Proof of concept that you can get an LLM to disbelieve its own lying eyes
Exclusively screenshots on Bluesky 😅
July 9, 2025 at 6:21 AM
Exclusively screenshots on Bluesky 😅
Technically this is pretty interesting, because nobody has as much high-quality training data as they want, and so nixing high-quality reporting as an input source and replacing it with Stormfront is already going to be a challenge…
July 9, 2025 at 1:50 AM
Technically this is pretty interesting, because nobody has as much high-quality training data as they want, and so nixing high-quality reporting as an input source and replacing it with Stormfront is already going to be a challenge…
I think part of the problem is that it’s possible to curate your feed pretty well to get rid of the hate-bait and just see what you want. It’s not until you try going back as a preference-naïve account that you see how bad it’s become
July 8, 2025 at 2:56 AM
I think part of the problem is that it’s possible to curate your feed pretty well to get rid of the hate-bait and just see what you want. It’s not until you try going back as a preference-naïve account that you see how bad it’s become
I have an unfinished draft that mentions a similar technique here: sgnt.ai/p/rag-trinity
RAG chunking isn’t one problem, it’s three | sgnt.ai
Existing articles often focus on a chunk as a singular concept: you split the article into paragraphs, say, and use these to feed the LLM, generate embeddings, and quote back to the user. But that's t...
sgnt.ai
July 7, 2025 at 4:54 PM
I have an unfinished draft that mentions a similar technique here: sgnt.ai/p/rag-trinity
This is a lovely way of putting it and I agree
July 4, 2025 at 6:01 AM
This is a lovely way of putting it and I agree
Process and accountability issue imo
July 4, 2025 at 6:00 AM
Process and accountability issue imo
I like the LaTeX explicit double hyphen as an alternative --
June 26, 2025 at 6:08 PM
I like the LaTeX explicit double hyphen as an alternative --
Can we start calling people “AI deniers”?
June 26, 2025 at 12:25 PM
Can we start calling people “AI deniers”?
Oddly I find ChatGPT too combative, and Claude to be too persuadable. Gemini answers 1 in 5 queries in the style of a press release. What an amazing time to be alive
June 11, 2025 at 2:17 PM
Oddly I find ChatGPT too combative, and Claude to be too persuadable. Gemini answers 1 in 5 queries in the style of a press release. What an amazing time to be alive