Viewing profile — SwtCyber

The "100% accurate and free of hallucinations" claim should probably be replaced with something much weaker

I think there's an underrated difference between information generation and pedagogy here. LLMs are very good at producing more explanation, yet "more explanation" is often exactly…

I think the key difference here is that you're using the LLM to create exercises, not to replace the learning material

The test I'd like to see: take a problem set or task you couldn't solve beforehand, learn the topic this way, then try to solve it without the LLM in the loop

One concern though: "100% accurate and free of hallucinations" is doing a lot of work. A second LLM pass can catch some mistakes, but it can also confidently agree with the first o…

That’s a direct result of how they’re fine tuned. RLHF and other mechanisms reward quick, locally correct answers that solve the user’s immediate problem. A reward for a solution l…

I think the best part about this benchmark is that they finally stopped pretending you can evaluate a complex engineering task with $ 5 worth of inference. If a task takes a human …

People still cook in houses with microwaves and wash dishes despite owning dishwashers

The future arrived quietly

Bradbury wrote rockets the way other writers wrote sunsets

[dead]

[dead]

[dead]

[dead]

That is an amazing sleep indicator: once the rabbit starts discussing thermodynamics, dad has left the building

The reading task can stay largely automatic until both streams try to use the same speech-production machinery at once

It really does feel like reading and counting can occupy separate lanes, while writing and counting are both trying to use the same internal narrator

This is a nice example of using interference as a window into representation

This seems potentially useful for attention-steered hearing aids. A system that waits for complete disengagement from the old speaker may react too slowly

The thing is this isn't a schema generation or Typescript bug at all. This is just how openai's function calling works under the hood. Their weights were fine-tuned for tool use to…

I would rather read an article with actual production experience migrating an agent, even if it is written in this style, than a perfectly crafted long read from another evangelist…

Its ironic that under an article with a ton of deep infrastructure insights half the comments are crying about the "forced writing style". What does it matter if claude helped the …

Its funny to see how researchers bypass Githubs praised guardrails with a simple word like "Additionally". It just proves that any attempt to build hard security boundaries inside …

[dead]

[dead]