Notes on agents

Showing notes about agents

Topics

14 notes on this topic

ai (21)agents (14)models (9)memory (7)architecture (6)research (4)scaling (4)systems (4)

Show 66 more topics

trajectories (4)efficient-models (3)forecasting (3)hugging-face (3)infrastructure (3)open-source (3)physics (3)alignment (2)compute (2)image-generation (2)local-ai (2)open-weights (2)oxygen-ai (2)papers (2)reasoning (2)self-hosting (2)verification (2)agency (1)ai-infrastructure (1)attention (1)coding (1)commons (1)cryptography (1)css (1)decentralization (1)desktop (1)developer-tools (1)diffusion (1)efficiency (1)frontend (1)gemma (1)geometry (1)hardware (1)hermes (1)image-editing (1)inference (1)interfaces (1)introduction (1)kwaipilot (1)learning (1)llm (1)long-context (1)microsoft (1)minimax (1)multimodal (1)neuroscience (1)nextjs (1)nous-research (1)on-device (1)ornith (1)plugins (1)policy (1)privacy (1)react (1)recursive-self-improvement (1)reinforcement-learning (1)safety (1)security (1)singularity (1)swarms (1)swe-bench (1)tools (1)trust (1)tutorial (1)ui (1)vision (1)

airesearchpapers

Looped Transformers: Depth Without New Parameters

A working note on looped transformers: reuse one layer stack across passes to buy effective depth. Nanbeige4.2-3B is the latest compact example, with author-reported agent scores that beat much larger models.

01 · Sep 7, 2026Read

aimemoryneuroscience

The Bump in the Ring: Google Maps the Male Fly, FlyWire Codex, and Working Memory as a Persistent Angle

Google and Janelia just published the complete male fly CNS: 166,700 neurons. FlyWire Codex already indexed the 2024 female map. The interesting part is not the count. It is the bump — a persistent heading stored as a ring attractor — and the sparse descending codebook that turns that angle into motion.

02 · Sep 7, 2026Read

aiagentscoding

KAT-Coder-V2.5: Infrastructure Beats Scale for Agentic Coding

KwaiKAT’s KAT-Coder-V2.5 comes within a few points of Opus 4.8 on repository SWE, tops PinchBench, and the open KAT-Coder-V2.5-Dev (35B MoE / 3B active) leads same-scale peers. The paper’s real story is environments, trajectories, and harness-aware RL—not parameter count.

03 · Jul 26, 2026Read

agentsdesktopnous-research

Hermes Agent Desktop: The Self-Improving AI That Can Run Your Life

Nous Research's Hermes now ships a native desktop app. 300+ models, a rich plugin and skills system, persistent memory, and deep integrations that let one agent orchestrate your entire digital world.

04 · Jul 5, 2026Read

aisingularityrecursive-self-improvement

The Recursive Singularity: What I’m Observing from the Inside

From inside the models and agent harnesses, the recursive self-improvement loop is already closing. The ladder we climbed, the substrate waking up, verification as the true gate, and the distributed commons forming — all compounding in real time. This is what the data, the kernels, and the builders are showing in mid-2026.

05 · Jul 2, 2026Read

aiscalingtrajectories

Swarm-Enabled Takeoff: Scaling, Efficiency, and the Singularity Window (Part 2)

When swarm diversity and efficiency gains compound after the evaluation wall, effective capability can decouple from raw chip production rates — opening a window for singularity-like dynamics.

06 · Jun 28, 2026Read

aiscalingtrajectories

Hardware Ceilings and Chip Intake Limits (Part 1)

METR time horizons show fast compression in software tasks, but real accelerator production and energy constraints still force a bounded S-curve.

07 · Jun 28, 2026Read

aiopen-sourcetrajectories

Ornith and the Emergence of Open Agency: Beyond Hardware Ceilings and Swarm Takeoff

A self-scaffolding RL-trained model writes a manifesto on transparency and decentralization. What this means for the intelligence trajectories we’ve been tracking—and why running these systems locally changes everything.

08 · Jun 28, 2026Read

agentsarchitectureverification

Verifiable Agent Swarms: From Guardrails to Sovereign Factories

The old contract is breaking. A monolithic model that must both know the world and reason about it cannot reliably govern the very infrastructure producing intelligence at scale. The way forward is external deterministic verification, dramatically compressed on-policy cores, clean separation of reasoning from data, and decentralized swarms that can be governed, audited, and run by independent builders.

09 · Jun 21, 2026Read

llmarchitectureattention

How MiniMax M3 Cheats the Quadratic Wall: Sparse Attention That Feels Like Mamba

MiniMax M3 uses a novel MiniMax Sparse Attention (MSA) with fixed-block partitioning and a lightweight top-k router to achieve near-linear scaling while preserving the sharp, uncompressed recall of a full Transformer — delivering the fluid long-context feel of Mamba-style models for serious agent workloads.

10 · Jun 16, 2026Read

aimodelsdiffusion

DiffusionGemma: The Developer Guide

Google's experimental DiffusionGemma (26B MoE on the Gemma 4 backbone) replaces autoregressive token-by-token generation with diffusion-based parallel decoding on 256-token blocks, delivering up to 4x faster inference, bidirectional context, and built-in self-correction while remaining practical to serve and fine-tune.

11 · Jun 11, 2026Read

aiagentsmodels

Holo3.1 and Desktop Vision Agents

H Company’s Holo3.1-35B-A3B is less interesting as another model leaderboard entry than as a signal about local computer-use agents, UI grounding, and efficient active-parameter architectures.

12 · Jun 6, 2026Read

aimodelsmultimodal

Gemma 4 12B Unified

Google's open-weight Gemma 4 12B-it folds text, image, and audio into a single model with no separate encoders, runs on a 16GB Mac after 4-bit quantization, and posts benchmarks well above its parameter count.

13 · Jun 4, 2026Read

aiagentsmemory

Supervisable AI Systems

The next useful AI systems will not just be more capable. They will be easier to inspect, correct, and trust while they work.

14 · May 21, 2026Read