2. Multi-Stream LLMs: new paper on parallelizing/separating prompts, thinking, I/O (arxiv.org)

The continued improvements in language model capability have unlocked their widespread use as drivers of autonomous agents, for example in coding or computer use applications. However, the core of these systems has not changed much since early instruction-tuned models like ChatGPT. Even advanced AI agents function on message exchange formats, successively exchanging messages with users, systems, with itself (i.e. chain-of-thought) and tools in a single stream of computation. This bottleneck to a single stream in chat models leads to a number of limitations: the agent cannot act (generate output) while reading, and in reverse, cannot react to new information while writing. Similarly, the agent cannot act while thinking and cannot think while reading or acting on information.
In this work, we show that models can be unblocked by switching from instruction-tuning for sequential message formats to instruction-tuning for multiple, parallel streams of computation, splitting each role into a separate stream. Every forward pass of the language model then simultaneously reads from multiple input streams and generates tokens in multiple output streams, all of which causally depend on earlier timesteps. We argue that this data-driven change remedies a number of usability limitations as outlined above, improves model efficiency through parallelization, improves model security through better separation of concerns and can further improve model monitorability.

21. Where are all the UK red telephone kiosks? (www.thek6project.co.uk)

Hello and welcome to the K6 project, a personal adventure to travel the length and breadth of the UK finding old red telephone boxes, the k6 used to be everywhere before mobile telephones became the prevalent form of telecommunication.

23. All the Bugs They Found (andreapivetta.com)

Last year I wrote a small WASM runtime in Go. How many security vulnerabilities do you think AI agents found in it?

Article Details

Browse by Date

Type to search HN and engineering blog articles
Press Escape to close  |  ↑↓ to navigate  |  Enter to open