food-for-thought

AI-Powered Workflows / smart if-statements. Structured outputs slot into ordinary software as fuzzy decision rules: classify, route, score, extract, or branch where hand-written logic is too brittle. The surrounding code constrains their freedom, making them easier to compose into reliable systems. Map-reducing over big data. Turn petabytes of data into features and insights. Real-time applications. 100ms speeds means you can use AI in your applications where UX is critical. Verify everything. Score, judge, verify, guardrail, and detect jailbreaks of LLM prompts, reasoning traces, and/or outputs.

Stop throwing AI-generated walls of text into conversations.

AX is a high-throughput, declarative orchestrator to run billions of autonomous agent workloads in a cluster. It runs on top of Agent Substrate for sandboxed execution and is built to run billions of tasks per cluster. If you have used Kubernetes, ax will feel similar.

How Claude marks AI-generated content

Check if a file was made with Claude

does AI merely improve efficiency, or does it alter how we think?

Putting it together Here is everything above in one place. A key, its diatonic chords, a progression, those chords broken into an arpeggio one note at a time, and a melody that sticks to the scale. About forty lines, no library, and it is the first thing I made with code that I would describe as music rather than as a demonstration

Memory Hardware Models 128 GB RAM Strix Halo ($3,600)DGX Spark ($4,300)Mac Studio M5 Max ($5,100)MacBook Pro M5 Max ($7,150) Qwen3.8-FlashGLM-5.3-Flash (degraded intelligence)DeepSeek-V4-Flash (degraded intelligence) 256 GB RAM 2x DGX Spark ($8,700)Mac Studio M5 Ultra ($11,300) GLM-5.3-FlashDeepSeek-V4-Flash 512 GB RAM 2x Mac Studio M5 Ultra ($22,600) GLM-5.3 2 TB RAM 2x TensTorrent Galaxy Blackhole ($320,000) Kimi K3

In this INDEX the numerals do not indicate the pages, but they refer to the engravings and the numbered paragraphs. Each page of the letter-press contains all the descriptive matter appertaining to the illustrations which face it.

Qwen3.8-27B-Uncensored-MLX An abliterated (refusal-removed) MLX build of Qwen's Qwen3.8-27B — 2 / 4 / 6 / 8-bit for Apple Silicon

In linear accelerator, injected electrons gain energy from an RF field. Ordinarily, the electrons would then enter a free electron laser and are immediately disposed of in a beam dump. But in an energy recovery linear accelerator (ERL), the electrons circle back into the RF field and lend their energy to newly injected electrons before exiting to a beam dump.

Taste Is All That's Left

September 1, 2017

when one party’s drones are destroyed by drones of another, it will have no other choice but to surrender

development of AI raises “colossal opportunities and threats that are difficult to predict now.”

the one who becomes the leader in this sphere will be the ruler of the world.

Frontier models are now generally very competent at understanding a terminal (or terminal-style) coding environment, and acting within it. Anthropic recently cutting down Claude Code’s system prompt by 80% is a clear sign of this

SIMD allows a CPU to operate on multiple values in parallel. For example, instead of comparing one byte at a time, a CPU can compare 4, 8, or even more bytes with a single instruction.

expert-designed harness can coordinate a large portion of auto-research loop, experimented in the form of writing research papers

AI companies are racing to build AIs that are smarter than humans in every way. In AI 2027, we predicted that this would result in either extinction or irreversible concentration of power.1Plan A is our positive vision for what should happen instead.

The scenario itself was written iteratively: we wrote the first period (up to mid-2025), then the following period, etc. until we reached the ending. We then scrapped this and did it again.

Write a future history of 2022. Condition on it, and write a future history of 2023. Repeat for 2024, 2025, etc. (I'm posting 2022-2026 now so I can get feedback that will help me write 2027+. I intend to keep writing until the story reaches singularity/extinction/utopia/etc.)

What 2026 looks like

rumoured list of papers that Ilya Sutskever gave to John Carmack

Intelligence vs. Cost per Intelligence Index TaskArtificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task

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.