AI

Find quality improvement loops, not just productivity loops.

t on LLMs and SQL highlighting why they don’t consistently work :

• “LLMs can write SQL, but they are often prone to making up tables, making up field”


• “LLMs have some context window which limits the amount of text they can operate over”


• “The SQL it writes may be incorrect for whatever reason, or it could be correct but just return an unexpected

... See more

The present findings also show that it is possible to develop systems that can instantly interpret emotional cues to provide immediate and intuitive feedback in a wide range of situations. This could lead to scalable, cost-efficient applications in various domains where understanding emotional context is crucial, such as therapy and interpersonal... See more

Project Lazarus is an initiative to acquire and permanently preserve the full, unfiltered operational history of defunct or inactive companies at scale. We focus on private codebases, version histories, internal documentation, post-mortems, experimentation logs, infrastructure tooling, and everyday work artifacts that collectively reflect how real... See more

The more I use language models, the more monstrous they seem to me. I don’t mean that in a partic­u­larly negative sense. Frankenstein’s monster is sad, but also amazing. Godzilla is a monster, and Godzilla rules.

Through extensive experimentation across diverse puzzles, we show that frontier LRMs face a complete accuracy collapse beyond certain complexities. Moreover, they exhibit a counter-intuitive scaling limit: their reasoning effort increases with problem complexity up to a point, then declines despite having an adequate token budget. By comparing LRMs

... See more