231–240 of 512 posts
A few questions: 1. Do you provide any kind of largest common subtree caching for cheaper input? 2. Have you tried auto-generating Lisp programs structurally? 3. Have you tried augmenting a Lisp language with a `choice` function that makes choices given a prompt, the environment, and the continuation stack?
(2-3) No, but that's kind of a sick cook ... Want to get access and try it? nathan@typesafe.ai
Earlier quoted context omitted.
His claim was that the title is misleading, not sure how it's relevant to that claim that you use "string models" (full LLMs). The original title before it changed less than an hour ago was: "Jev: New frontier model 40-400x cheaper and 20-200x faster" I'm going to agree that was misleading. And on the second point: >>Also "can't hallucinate" seems wrong? Sure, it can't emit an invalid type, but it can still emit a co…
> Type safety is not factual correctness. I very much agree with this and want to hone in on where do actually disagree. Would you say a linear classifier hallucinates?
You’ve already agreed that this doesn’t establish correctness. An approve for an unauthorized action still meets the schema guarantee.
That’s why I find the messaging misleading. You’re acknowledging the limitations in these replies while defending the broader reliability pitch.
Even granting that each answer is calibrated individually, that doesn’t establish calibration of the decision that combines them.
Sure, I can threshold a composite score, but there may be many wrong answers with the same score. An unauthorized action doesn’t become acceptable because it scores highly on the other dimensions.
I still have to define the constraints and test which wrong actions get through the complete workflow on my own data. That’s a substantial part of the work being pushed back onto the developer.
Earlier quoted context omitted.
What's different about this particular model that worries you?
it doesn't require nearly as much compute as normal LLMs. anything depending on increased datacenter and compute spending would be threatened.
The whole page reads like it was vibe-written by an AI. If I'd built something as disruptive as this claims to be, I'd have spent at least fifteen minutes writing the announcement myself. Every time I see 'we' in an announcement like this, I picture one guy alone in his basement.
Is there a bottleneck which would hinder putting this architecture in charge of a humanoid? Would it be able to operate continuously, for example in conjunction with an LLM for long-term reasoning? Doom seemingly works extremely well.
The whole page reads like it was vibe-written by an AI. If I'd built something as disruptive as this claims to be, I'd have spent at least fifteen minutes writing the announcement myself. Every time I see 'we' in an announcement like this, I picture one guy alone in his basement.
unfortunately all hand-written :( my chief-of-staff does unironically handwrite em dashes though
Earlier quoted context omitted.
Technically speaking when you send the prefix “The capital of France is “ into an LLM it will also produce probabilities across its whole vocabulary.
… which they could provide in their APIs but are vehemently opposed to because it makes distillation much easier, and faster.
Earlier quoted context omitted.
it doesn't require nearly as much compute as normal LLMs. anything depending on increased datacenter and compute spending would be threatened.
a world where people eat so they can feed Big Computer sucks. We need Little Computer, driving robots in the fields.