152334Hhttps://152334H.github.io/152334H Personal BlogHugo -- gohugo.ioenTue, 14 Jul 2026 00:00:00 +0800Are exploits free?https://152334H.github.io/blog/kctf-eval/Sat, 14 Feb 2026 00:00:00 +0800152334Hhttps://152334H.github.io/blog/kctf-eval/<p>For various reasons, I had to develop a kernel n-day exploit last week.</p>Nothing to be saidhttps://152334H.github.io/blog/july/Tue, 14 Jul 2026 00:00:00 +0800152334Hhttps://152334H.github.io/blog/july/<p>title</p>Some Notes on Alignment Blogshttps://152334H.github.io/blog/alignment-blog-notes/Sun, 14 Jun 2026 00:00:00 +0800152334Hhttps://152334H.github.io/blog/alignment-blog-notes/These are quick self-notes I wrote this week, while scrolling various AI Alignment related posts online.

There are no insights here, just mundane reading & paraphrasing to ensure I ‘get it’.

]]>Notes on POIShttps://152334H.github.io/blog/pois/Thu, 14 May 2026 00:00:00 +0800152334Hhttps://152334H.github.io/blog/pois/Post Orgasmic Illness Syndrome (POIS) is, allegedly, a Rare Sexual Disorder whose sufferers experience some combination of flu/fever/fatigue/irritability/aphasia/… rapidly after any orgasm.

]]>Personal ratings of how models criticise mehttps://152334H.github.io/blog/navel-gazing/Tue, 14 Apr 2026 00:00:00 +0800152334Hhttps://152334H.github.io/blog/navel-gazing/<p>Instead of a garbage monthly post, let&rsquo;s look at how different models respond to my garbage.</p>Things worth doinghttps://152334H.github.io/blog/things-worth-doing/Sat, 14 Mar 2026 00:00:00 +0800152334Hhttps://152334H.github.io/blog/things-worth-doing/<p>Most of my life has been dedicated towards intellectual excellence, but continuing to do so would be a mistake.</p>Truncated Thoughts on 2025https://152334H.github.io/blog/2026/Thu, 01 Jan 2026 00:00:00 +0800152334Hhttps://152334H.github.io/blog/2026/<p>It has been, overall, a pretty shit year.</p>Time To Thinkhttps://152334H.github.io/blog/time-to-think/Tue, 04 Feb 2025 01:02:03 +0800152334Hhttps://152334H.github.io/blog/time-to-think/I don’t remember what it’s like to think with more than 60 seconds of context.

]]>Calculating the Cost of a Google Deepmind Paperhttps://152334H.github.io/blog/scaling-exponents/Tue, 30 Jul 2024 00:00:00 +0800152334Hhttps://152334H.github.io/blog/scaling-exponents/Recently, GDM released a great paper titled, Scaling Exponents Across Parameterizations and Optimizers, in which they conduct over 10,000 LLM training runs to obtain optimal hyperparameters under different regimes.

After reading it (it was great), I wanted to test my understanding of the paper by tallying up all experiments conducted within, calculating the total compute cost it would take to replicate the paper.

]]>DeepSeek Core Readings 0 - Coderhttps://152334H.github.io/blog/deepseek-0/Sun, 30 Jun 2024 00:00:00 +0800152334Hhttps://152334H.github.io/blog/deepseek-0/Paper summary: 1.3B to 33B LLMs on 1/2T code tokens (87 langs) w/ FiM and 16K seqlen. Strong effort in constructing pretraining data from Github from scratch, with repository-level samples. Evals beat OSS code models solidly + GPT-3.5 a bit; Coder-7B > CodeLlama-33B often.

They don’t spend much effort on Instruction tuning. They commit a continued pretrain of DeepSeek LLM -> Coder: I believe it underperforms; they don’t.

]]>