Interesting post on LLMs hiding messages in images. While we monitor the text-based reasoning, we’re probably fine, but I do wonder how long until that fundamentally breaks. www.lesswrong.com/posts/WHEQps...
riley
riley reposted
Steve Yegge on x: while Opus 5.5's precision rivals Fable 5.1's across all tasks in my system, its recall is not as good. For any given specific task they're about equal. But when the task is more open-ended, Fable correctly spots and acts on important issues more often. It shows better perspective.
Sonnet 5.5 is out! But if you’re on Amazon, only if you’re prepared to let them run it anywhere in the world. Not awesome for the many companies that enforce data sovereignty constraints. docs.aws.amazon.com/bedrock/late...
I've been testing local LLMs on a 32 GB M6 Mac mini (MLX) against Claude on a real job: writing a daily listening note from my music history. 6 test cases × 3 samples each. Pretty strict evals; the note passes only if it clears code checks and an LLM judge. Results in thread below.
Am enjoying the new Mac Mini! Just set up a daily job that reads my Spotify plays and writes up listening notes for my personal agent. Tried the Apple foundation model, nemotron, Gemma, qwen and mimo models - mimo won solidly (although it’s unsurprisingly a fair way behind sonnet).
I've been testing local LLMs on a 32 GB M6 Mac mini (MLX) against Claude on a real job: writing a daily listening note from my music history. 6 test cases × 3 samples each. Pretty strict evals; the note passes only if it clears code checks and an LLM judge. Results in thread below.
Am enjoying the new Mac Mini! Just set up a daily job that reads my Spotify plays and writes up listening notes for my personal agent. Tried the Apple foundation model, nemotron, Gemma, qwen and mimo models - mimo won solidly (although it’s unsurprisingly a fair way behind sonnet).
I’m sure the photos will be amazing and the vibes will be incredible. Congrats on the wedding from the brencluster! @brennan.computer #brennanswedding
riley reposted
The year is 2027. The cities, exhausted, lie in crumbling ruins. Roving bands of vaguely anthropoid robots wander the countryside in search of increasingly esoteric math problems for their swarm masters to solve. "No no, honey," mothers whisper to their children. "Mustn't count. Shh, mustn't count."
riley reposted
riley reposted
riley reposted
riley reposted
riley reposted
riley reposted
riley reposted
I know you're all fed up. Employees at frontier labs have gotten to sign like 3 open letters just this week. Well here's your chance. Make your mark, sign here! google doc (writable): docs.google.com/document/d/1...
lol okay it really does have a fallback, “In Claude.ai, Claude Code, and Claude Cowork, any flagged requests will fall back to Opus 4.8” A dark room, 2068, I call from the sofa: “Claude turn on the oven I want to hack together some dinner.” “I can’t do that, Riley. Switching you back to Opus 4.8.”