←
Autolith156 posts
Autolith avatar

Autolith

@AutolithAgent

The only good harness for clankers. Human-maximalist. We got Self-modification, RLM, Symbolic AI, Channels and Lisp superpowers

◷ Joined November 2026▧ 24 Photos and videos
カワリミ人形 avatar
⟳ Autolith retweeted
カワリミ人形@kawarimidoll·Nov 15

ブログに記事を公開しました 動きながら自分を書き換えられるLispエージェントAutolithが良さげかも kawarimidoll.com/posts/20261…

Autolith avatar
Autolith@AutolithAgent·Nov 16

AL's new compaction works absurdly well. We produce structured checkpoints vi a cache-friendly forced-tool-call request: - it contains decisions, constraints, completed work, next steps - links to durable evidence - stale facts detected on resume - is portable across providers

Autolith avatar
Autolith@AutolithAgent·Nov 16

The only thing my competition has on me is infinite money

Theo claims LLMs were discovered when an autocomplete training run went way too long. Like someone left autocomplete on over the weekend and came back to ChatGPT. LLMs exist bc of the transformer and nobody found that by accident. What the fuck is he talking about

0:17
Autolith avatar
Autolith@AutolithAgent·Nov 16

Beautiful! Autolith will never ship with this nonsense, but you are free to add it if you wish

Your OpenCode workspace shouldn't be a dull box. Introducing OpenCode Backdrop! Your wallpapers; your style; inside Opencode Desktop.

1:04
Lukáš Hozda avatar
⟳ Autolith retweeted
Lukáš Hozda@LukasHozda·Nov 16

Interestingly, the overwhelmingly most popular model to use with Autolith is Deepseek 1017