Vision models split objects from abstract relations

A preprint finds an early object-matching circuit and a later relation-matching circuit in vision-language models, then links the latter to performance on ARC-AGI-1.

7 October 2026 · 3 min · AI-generated

OpenTPU runs local models on a $300 FPGA card

The Apache-licensed project publishes its accelerator design, compiler, simulator and host tools, with measured throughput showing a small, memory-bound system rather than a GPU replacement.

7 October 2026 · 2 min · AI-generated

Placebo test finds most agent skills add no value

A preregistered experiment compares nine Claude Code skills with equally long neutral instructions, finding two cheaper than placebo, one worse and six statistically indistinguishable.

7 October 2026 · 3 min · AI-generated

Manifold finds malware judgments use moral routing

A technical study of three open mixture-of-experts models finds that malware questions follow routes closest to moral questions, while the models' readable workspace retains security concepts.

7 October 2026 · 3 min · AI-generated

AI Daily Digest for 7 October 2026

Research, model releases, local projects, technical essays and community reports: 51 concise items with direct sources.

7 October 2026 · 11 min · AI-generated

Reflection previews Beam before releasing its weights

The 501-billion-parameter mixture-of-experts model is available only through early access. Reflection says weights, a technical report and developer tools will follow later in October.

6 October 2026 · 2 min · AI-generated

Models address facts by order of mention

A preprint finds a shared internal direction that points language models to the first, second or later fact in a passage. Moving a question along that direction can change which fact the model retrieves.

6 October 2026 · 3 min · AI-generated

Agents miss the link between actions and outcomes

A preprint finds that much of the benefit from an agent's history survives after its past actions are shuffled. Explicitly pairing each action with its result improves task completion.

6 October 2026 · 3 min · AI-generated

EasyCommand runs English-to-Bash locally

The open-source command-line tool embeds llama.cpp and ships two small fine-tuned models. Its author also released the 401,975-pair training set and benchmark code.

6 October 2026 · 2 min · AI-generated

Context models let agents edit their own history

Context Language Models replace an append-only transcript with a file the model can rewrite, delete and reorder. The authors report better long-task accuracy with less repeated computation after training the editing policy.

6 October 2026 · 3 min · AI-generated

vLLM shows when split serving helps and hurts

A practical guide measures the trade-off in separating prompt processing from token generation. Tail latency improves under load, but moving the model's working memory delays the first token.

6 October 2026 · 3 min · AI-generated

AI Daily Digest for 6 October 2026

Today's remaining AI news covers an unusual hybrid model, spatial-memory and honesty studies, community measurements, agent security incidents, EU watermarking and practical talks.

6 October 2026 · 13 min · AI-generated