After each reply, Anthropic adds one hidden turn and Claude returns a JSON safety flag in ~10 tokens, under 2% of compute. The KV cache makes it cheap.
Anthropic's Safeguards team published how Claude monitors its own conversations for misuse. After each reply, the system appends a short hidden instruction aski...
via XSpawn, 10 people, ships 107 changes an hour with agents and no pull requests. What I'd copy (hard gates, cheap undo) and what I wouldn't.
Jacob Sansbury wrote up how Spawn works, a ten-person company building a multiplayer game engine where players change the world by prompting an in-game agent. T...
via Simon WillisonMistral Large 4's open weights are 1,060.6 GB in FP8 and 610 GB in NVFP4. What fits on one 8-GPU node, KV cache per token, and API vs renting GPUs.
Claude Code resends each working background agent's transcript every ~30s for a status line. One team measured 16.4% of spend; Anthropic says ~2%.
Flamerix AI published a gist on October 26 about a side query inside Claude Code that most people never see. While a background agent is working, Claude Code se...
via Hacker News"AI may well be able to write massive software projects “from scratch”, but that almost certainly isn’t the fastest / highest performance / highest security / most token efficient way to do things. Good building blocks matter. In addition to RL’ing the agents on final task loss, we should try to get them to regularize the building blocks as well. What would the standard library look like that makes the agents most effective? It is likely at the limit that it turns out to be some alien organization of code, but given the existing human-bias in training, I bet that in the near term it would be lovely code that old programmers would appreciate. I suspect the same could be said for mathematics, but that is out of my lane."
— John Carmack
Gemini 4 Carbon will cost $4/$20 per million tokens after its intro price, the same as Opus 5.5. Its implicit-only cache decides which is cheaper.
Anthropic's S-1: $16.3B revenue in H1 2026, 80% of it metered tokens, and cost per task named as the lever it competes on. Notes from the filing.
Anthropic, PBC: Form S-1 registration statement (filed with the SEC on October 26, 2026) Anthropic filed to go public on the Nasdaq Global Select Market under t...
via Hacker News"If you care about quality only, pick Astra. If you're a bit price sensitive, pick Sol. If you're very price sensitive, pick Terra or Luna."
— Ted Sanders
Long-running AI agents lock onto one plan. Four October 2026 studies point to one fix: forget and restart. What it costs and what to hand off.
Apollo's chief economist sees no AI payoff outside big tech, and says companies now treat token spend as a cost center. What builders should do.
No Signs of AI Payoff Outside the Tech Sector (Torsten Slok, Apollo's chief economist, The Daily Spark, October 24, 2026) Slok's note is five charts and four sh...
via Hacker NewsMax Woolf's timeline of OpenAI and Anthropic price cuts, and why cache-read prices are the ones that matter for coding agents.
OpenAI and Anthropic cut their LLM prices by up to 80% within a few months. Why? (Max Woolf, October 25, 2026) Max Woolf lays out every OpenAI and Anthropic pri...
via Hacker News"It's a simple question for any enterprise. Would you like something that's 10 percent of the cost if it's 90 percent as good as the best, or do you want to pay that 10 times higher cost?"
— Arvind Krishna
Kimi K3.1 Pro lists at half Opus 5.5's price, but cache hits narrow the gap. Session cost math, Moonshot's benchmarks, and the cyber data it removed.
OpenAI's official CLI has a tokenizer command that counts and inspects tokens locally, with no API key or network. Commands and real output.
Tokens are the chunks of text an AI model reads and bills you for. See how tokenizers split text, why Gujarati costs more, and how to count them.
How to choose an LLM: set hard constraints, test candidates on your own eval set, then compare cost per solved task, not price per token. With a cost script.
Prompt caching lets an LLM API reuse work on a prompt prefix it has already processed, cutting input cost and latency. How it works, prices, and a Python demo.
LLM cost per task is each call's tokens times their prices. For agents, cached input dominates. A runnable calculator with GLM-4.7, GPT-5.2, Sonnet 4.5.
Sparse attention lets each token attend to a few chosen earlier tokens. How DeepSeek V3.2 does it, why long prompts get cheaper, and a runnable numpy demo.
Claude Opus 4.5 costs $5/$25 per million tokens and adds a beta effort setting. How effort changes token spend and cost per task, with a runnable script.
A context window is how many tokens a model handles per request. Gemini 3 Pro takes 1M, but past 200k each token costs double. Runnable cost script inside.
Reasoning models write hidden thinking tokens before answering, billed as output. How GPT-5.1's reasoning effort works, with a runnable cost script.
Code execution with MCP lets an agent call tools from code, so definitions and big results stay out of context. How it works, with a runnable token count.
DeepSeek released R1 on 20 January 2025 under MIT, at $0.55 per million input tokens, with 79.8% on AIME 2024. What that does to a reasoning-search bill.
LLM latency is time to first token (TTFT) plus output tokens times inter-token latency. What each metric measures, what moves it, with a Python model.
o1-preview launched 12 September 2024. Thinking is billed as output, the chain of thought stays hidden, and the IMO score in the post is not the preview.
LLM routing sends each query to the cheapest model likely to answer it well; cascades try a small model first and escalate. How both work, with a Python sim.
Claude 3.5 Sonnet launched 21 June 2024 at $3 and $15 per million tokens, with Artifacts and a 64% internal coding score.
GPT-4o launched 13 May 2024 at $5 and $15 per million tokens, half of GPT-4 Turbo, with text and vision in the API.
GPT-4 launched 14 March 2023 at $30 per million input tokens for an 8,192 context. What the system card admits, priced against the 32k window.