
Astra for Coding: Why Are We Doing This Again?
Some thoughts on Astra and newfangled long-horizon models.

How I Bypassed Claude Opus’s CBRN-E Safeguards
A black-box jailbreak using model-authored state steering, plus an outside-in reconstruction of the safeguards it bypasses.

Recursive Language Models
We propose Recursive Language Models (RLMs), an inference strategy where language models can decompose and recursively interact with input context of unbounded length through REPL environments.

Recursive Language Models: the paradigm of 2026
How we plan to manage extremely long contexts
.png?v=c8c07d4bf43b)
Recursive Language Models
We study allowing large language models (LLMs) to process arbitrarily long prompts through the lens of inference-time scaling. We propose Recursive Language Models (RLMs), a general inference paradigm that treats long prompts as part of an external environment and allows the LLM to programmatically examine, decompose, and recursively call itself over snippets of the prompt. We find that RLMs can successfully process inputs up to two orders of magnitude beyond model context windows and, even for shorter prompts, dramatically outperform the quality of vanilla frontier LLMs and common long-context and coding scaffolds (e.g., on GPT-5 by a median across the evaluated benchmarks of $26\%$ against compaction, $130\%$ against CodeAct with sub-calls, and $13\%$ against Claude Code) across four diverse long-context tasks while having comparable cost. At a small scale, we post-train the first model around the RLM. Our model, RLM-Qwen3-8B, outperforms the underlying Qwen3-8B model by $28.3\%$ on average and even approaches the quality of vanilla GPT-5 on three long-context tasks. Code is available at https://github.com/alexzhang13/rlm.

PrimeIntellect-ai/prime-agent
A self-improving RLM agent for coding workflows and long-running autonomous tasks.

Ways to think about token pricing — Benedict Evans
AI is in a supply crunch today, but what happens when we come out of it? How and where will supply, demand, price, capacity and capex get back into equilibrium? Today, model labs can name their price, but why won’t they end up as low-margin commodity infrastructure?

Hermes Agent Documentation | Hermes Agent
The self-improving AI agent built by Nous Research. A built-in learning loop that creates skills from experience, improves them during use, and remembers across sessions.

Impeccable: Design skills for AI harnesses
1 skill, 23 commands, and curated anti-patterns for impeccable frontend design. Works with Cursor, Claude Code, GitHub Copilot, Gemini CLI, and Codex CLI.

rtk-ai/rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies