Ben Carson @mensmachina.com · 07/10/2026Let me just break out the ol’ electron microscope to construct the world’s tiniest violin. 100
Ben Carson @mensmachina.com · 26/09/2026I saw this going around and it made me think. These are my 9 most formative games. A bunch more that I’ve enjoyed, but these have stuck with me, or influenced me. Shoutout to Quake, which was my gateway to C and a career in software engineering. 320
Ben Carson @mensmachina.com · 18/09/2026Looks like it scores pretty high on ObscureBench, the benchmark based on the number of benchmarks I don’t immediately recognise. 0300
Ben Carson @mensmachina.com · 27/08/2026A lot of folks thought Ox Alpha was a new Fable/Sol class model - and it turned out to be GLM-5.3-Flash. This is not a dunk, but I think this means most tasks people do don’t require models of this class. This is a good thing! 121
Ben Carson @mensmachina.com · 30/07/2026I did have to, after Claude suggested that it should cold email Shane Gero for the tag data set. 060
Ben Carson @mensmachina.com · 30/07/2026I’m going to hit it with a “no again the goal is that we have highly inteligent [sic] model as good top researcher, we want to find new whale language” 1210
Ben Carson @mensmachina.com · 26/07/2026There wasn’t much grass to touch, and the snow wasn’t that thick, but it was a good day nonetheless. 000
Ben Carson @mensmachina.com · 09/07/2026Artemis by Nic Fiddian-Green, while it was installed on The Trundle overlooking Goodwood. I took this picture of it while visiting family in Chichester in 2010. It was such an odd thing to find there, like it was the Monolith from 2001. 010
Ben Carson @mensmachina.com · 04/07/2026"You are the embodiment of the Gang of Four and Jose Valim all rolled into one. Please review this project and document a set of software architecture improvements that could be made." 030
Ben Carson @mensmachina.com · 02/07/2026I made this for my wife recently because of the revolving door of plagues that go through our house. 010
Ben Carson @mensmachina.com · 29/06/2026Or mayhap Jeffery a ring of websites, a “webring” as it were. 171
Ben Carson @mensmachina.com · 27/06/2026This one went a bit too far into the borders of Flavour Town, but today I learned you can sign your crêpes. 010
Ben Carson @mensmachina.com · 11/06/2026Disappointed to discover that Fable doesn’t think what I’m doing is frontier LLM research. 170
Ben Carson @mensmachina.com · 03/06/2026Fork. Ok, this is my last one, we get it, you love forks. 000
Ben Carson @mensmachina.com · 30/05/2026My comprehensive review of Opus 4.8: the model likes forks. 350
Ben Carson @mensmachina.com · 30/05/2026You can bliss them out, but it seems to be bad from an alignment perspective - sycophancy, factuality robustness, privacy awareness. Conversely, anger leads to toxicity, but strengthens resistance to data leakage. So maybe steering models towards the Bruce Banner personality would be good? 010
Ben Carson @mensmachina.com · 20/05/2026So, why? RLHF results in assistant personas, which may not reward emotional expression. In fact an interesting result I observed was that as the stress conditions increased, so did the “serenity” emotion sub-scale. 110
Ben Carson @mensmachina.com · 20/05/2026Good news is that Gemma E2B is largely concordant. Its outputs reflect its internal state. We start seeing something interesting in 31B. In 31B there is a lot more suppression. 110
Ben Carson @mensmachina.com · 20/05/2026This is true of both the smallest E2B variant and the 31B variant. It roughly maps to the circumplex model of human affect, where emotions have both a valence (positive/negative) and arousal (high/low). Valence is a stronger signal however in the residual activations. 110
Ben Carson @mensmachina.com · 02/05/2026I think it might be PLE - this is my graph of PLE gate norms from my first hacky attempt. 110
Ben Carson @mensmachina.com · 02/05/2026I've got a peak valence correlation on layer 8, and a peak arousal on layer 25. Not identical to what you got, but I feel a lot better about seeing an effect now. 110
Ben Carson @mensmachina.com · 02/05/2026Figured it out - your repo helped a lot. De-noising didn't have as big an effect as I thought it would. One of the hacks I did in the first notebook was reading last token activation. I forgot that I needed to implement token pooling still, which they talk about in the Anthropic paper. 230
Ben Carson @mensmachina.com · 30/04/2026Here's the top positive and negative valence emotion concepts that e2b responds to. The massive difference in power between the positive and negative emotions is fascinating. 120
Ben Carson @mensmachina.com · 30/04/2026I don't think that methodology is quite right though - it's selecting for extremes along one axis, valence. Still, a germ of an idea. What is interesting is what emotion concepts have the greatest steering impact on the model. 100
Ben Carson @mensmachina.com · 30/04/2026Things have gotten more interesting as I've tried to scale up. I'm struggling to find a PC that cleanly matches valence. My first attempt used 20 representative emotions, with polar valence and arousal labels (+1,0,-1). I've been trying 174 emotions, labeled using NRC-VAD (Mohammad et al, 2025). 4302
Ben Carson @mensmachina.com · 27/04/2026Claude is taking a little holiday. Now I have to write code like a peasant. Or read some papers instead. 120