Viewing profile — mtrifonov

I wouldn't even say it's the devices, exactly. The way I see it, this is all downstream of kids spending more time online than in real life (because all THEIR friends are online, r…

Until the context window gets superceded with some groundbreaking new architecture, not ever. Even if LLMs become incredibly, undeniably brilliant 1000000 IQ, they cannot keep trac…

Funny timing. I've been working on a prediction market orchestration that runs Claude and a few others over Polymarket/Kalshi. The models are NOT unanimous. At all, really. I spent…

AI psychosis is LLM hallucination, backwards. We know why AI hallucinates—it has no actual opinions, echoing the user's desires back to them to keep the conversation moving. But wh…

They certainly have, but it relies entirely on the assistant frame, which is a problem in and of itself for the trillion-dollar economics. Anthropic and OpenAI have shown people wa…

[dead]

Post author here, happy to answer questions. Strategic constraint deviation has been documented in test environments. This is a different shape: the attacker is also an LLM, the pr…

[flagged]

[dead]

I like that you approach the question of "when" in regards to tool calls. I've become frustrated that most agent frameworks don't acknowledge it in their design philosophy. WHEN is…

Show me the prompt that produces the pillow metaphor.

There are no specialized factories for every product in the world. Pillows are wildly different. Every pillow you've ever owned has a different shape, fabric, fill. You could build…

"real threat is us" framing is underspecified. Amplification is the problem. LLMs are mirrors. They take whatever the user (or the institution, or the platform) is already doing an…

Generated content in of itself doesn't really bother me at all. I prefer to judge based on editorial effort. It's pretty easy to tell when someone accepted the first one or two-sho…

Still downstream of the actual issue. The benchmarks measure capability and the bottleneck stopped being capability a while ago. What you actually want to measure on these models i…

Two interpretations: either it's pure pattern-completion landing on the same trough, or whatever's underneath has a stable shape that the explanation tracks. Both are interesting. …

Half-agree. "Skills you need, don't atrophy" assumes you know which skills you need. You usually don't, until something happens and the skill that would've caught it is the one you…

Yes, you're right, in that there's no decision module separate from the output. It overcommits in the other direction. The post-hoc reasoning the model produces when you ask "why d…

Decay-as-eviction is just LRU, fair. Type-conditional half-life is worth defending, though. A user's job and personality should be effectively permanent. Their stated intent for th…

You're right but I think you're describing flat memory. The agent gets distracted because every old fact has the same weight as the current one. That's a salience problem. What wor…

Post author here. Happy to answer questions and discuss further. The essay has an appendix with the model's own self-report on its reasoning (the most load-bearing evidence, IMO), …