Coding an Agent: Steering a Local Model
Author(s): Enzo Lombardi Originally published on Towards AI. Directional Edits in DS4, or why a slider can do what a fork of the weights cannot Most of what you change about a language model’s behaviour you change from the outside. You write …
Coding an Agent: Decisions Without Decoding
Author(s): Enzo Lombardi Originally published on Towards AI. Reading answers out of a hot KV cache instead of generating them Most of what a coding agent asks its model is not a question that needs an essay. Is this conversation worth remembering. …
Introducing System One Models & Laya (and Jev)
Author(s): Enzo Lombardi Originally published on Towards AI. The classifier that never writes a word TypeSafe’s Jev announcement did the rounds properly: a frontier model that does not generate text, returns typed values with calibrated probabilities, and answers in 70 to 500 …
Introducing System One Models & Laya (and Jev)
Author(s): Enzo Lombardi Originally published on Towards AI. The classifier that never writes a word TypeSafe’s Jev announcement did the rounds properly: a frontier model that does not generate text, returns typed values with calibrated probabilities, and answers in 70 to 500 …
Multi-Token Prediction and Its Descendants
Author(s): Enzo Lombardi Originally published on Towards AI. How MTP, DFlash, DFlash 2, and DSpark each attack the same bottleneck Text generation is embarrassingly serial. To produce token number 200 a transformer needs token 199, which needs 198, and so on back …
Watermarking Text Generation Efficiently
Author(s): Enzo Lombardi Originally published on Towards AI. Or Why What You Recently Read About AI Watermarking Is Probably Wrong Most explanations of AI watermarking describe something that does not exist. They talk about hidden Unicode characters smuggled between words, or invisible …
🦀 Building AI Agents in Rust – part 11
Author(s): Enzo Lombardi Originally published on Towards AI. Crossing into C Part 10 got Eugene talking to DwarfStar without a socket, but it didn’t get rid of the process boundary. DwarfStarProvider still spawns ds4 as a child, writes a line to its …
🦀 Building AI Agents in Rust – part 10
Author(s): Enzo Lombardi Originally published on Towards AI. A provider with no socket Every provider Eugene has spoken to so far, going all the way back to Part 6, ends the same way: a URL, a header, a JSON body over HTTP. …
🦀 Building AI Agents in Rust – part 9
Author(s): Enzo Lombardi Originally published on Towards AI. Sandboxed code execution The eight previous parts gave Eugene careful, narrow capabilities: reading files inside a canonicalised sandbox, calling a handful of well-typed skills, talking to other agents, persisting memory, going through an open …
Building AI Agents in Rust — part 4
Author(s): Enzo Lombardi Originally published on Towards AI. State machines for multi-step tasks The loop in Part 1 handles a class of question that fits in one breath: read this file, list that directory, answer the user. Two turns, three turns, done. …
Building AI Agents in Rust — part 5
Author(s): Enzo Lombardi Originally published on Towards AI. Multi-agent crews The single-agent loop in Part 1 was enough for one question, one tool, one answer. The state machine in Part 4 handled a task with phases. Neither helps when the work itself …
Building AI Agents in Rust — part 3
Author(s): Enzo Lombardi Originally published on Towards AI. Skills as traits Two tools fit in a match statement. Three start to feel cramped. By six, the dispatcher is a swamp of clones, retries, error formatting, and case branches that all look almost …
Building AI Agents in Rust — part 2
Author(s): Enzo Lombardi Originally published on Towards AI. Prompt architecture The Part 1 system prompt was a single string literal. About sixty words. It told Eugene to answer questions about a Rust project and call read_file when it needed to see what …
Recent Posts
