food-for-thought

Everything is Logarithms

Logarithms are Vectors

Moving forward, the industry cannot continue to train bigger and bigger models since their intelligence not only plateaus but often will get worse

GPT-5.5 and DeepSeek V4 Pro are two of the clearest hallucination leaders, despite being absolutely huge. Because of their immense size they simply did not learn how to say “I don’t know”

.gitignore Isn’t the Only Way To Ignore Files in Git

You can do things like change the local context window and watch performance improve or degrade, and really dig into how your tokens are processed on the GPU. You can change the system prompt, the quantizations. You can pit models against each other. You can also change and introspect the harness side. The possibilities are endless, and the tools only keep getting better.

YASA's 37 kg stackable 750R motor delivers 800Nm and >5kW/kg with an axial length of 98 mm

proposed lightweight radiator for the dissipation of waste heat generated by power plants, propulsion or spacecraft systems in space.

Our preliminary findings show that the iterative Code Review stage accounts for the majority of token consumption for an average of 59.4% of tokens. Furthermore, we observe that input tokens consistently constitute the largest share of consumption for an average of 53.9%, providing empirical evidence for potentially significant inefficiencies in agentic collaboration.

So what’s actually different between GPT and Claude and Gemini and LLaMA? Public details vary, and the proprietary models do not publish every architectural choice. But at the level this post is covering, they broadly sit in the same transformer-family design space.

CS336: Language Modeling from Scratch

The twenty claims in this corpus with the widest spread between the highest- and lowest-bucket frontier verdicts. These are claims where the panel doesn't just disagree — it disagrees substantively, with at least one model picking a verdict ≥2 buckets away from another.

Flipper One — we need your help

Ultimate collection of online dos games

Live coding session with Boris Cherny and Jarred Sumner

Thermodynamic Computing System for AI Applications

Openrouter for comparable models is 1/3rd the price and ~2x the speed

The harness is built from five extension points—CLAUDE.md files, hooks, skills, plugins, and MCP servers—each serving a different function. The order in which teams build them matters

The sefirot are the ten spheres on the Tree of Life. Each sefirah (singular of sefirot) represents a different aspect of the Divine, as well as aspects of human consciousness and existence. These are, from top to bottom

software bug that seems to disappear or alter its behavior when one attempts to study it

The same 732-byte Python script roots every Linux distribution shipped since 2017

collection of principles and patterns that shape software systems

Migrating from DigitalOcean to Hetzner: From $1,432 to $233/month With Zero Downtime

Code is run more than read

Five git commands that tell you where a codebase hurts before you open a single file. Churn hotspots, bus factor, bug clusters, and crisis patterns.

Gemma 4
31B IT

The omni-9 are Alibaba, Alphabet, Amazon, Apple, Huawei, Meta, Microsoft, Samsung, and Tesla

These 18 potential future arenas could yield a total of $29 trillion to $48 trillion in revenues and $2 trillion to $6 trillion in profits by 2040

What actually happens when you type a message into Claude Code? The agent loop, 40+ tools, multi-agent orchestration, and unreleased features, mapped straight from the source.

Chess in Pure SQL