AivexaNewsSearch
AI news for builders and product teamsUpdated Nov 18, 2026, 10:01 UTC

AI news, straight from the source.

Releases, research, and ideas for developers and product teams. Updated every hour.

Across the feeds

Newest first

SOP-Bench: A new benchmark for evaluating AI agents on real business procedures

Amazon released SOP-Bench, an openly available benchmark that measures how well AI agents execute real standard operating procedures authored by domain experts across 12 business areas, with more than 2,000 tasks, functioning tools, and ground-truth answers. Testing two baseline agents across 11 frontier models showed that newer models sometimes scored lower, extra tools nearly halved success on one procedure, and no single model-agent pairing won everywhere.

Read original

How I built this

Ben's Bites describes how the author set up a fresh personal agent using a folder of instruction and memory files, then revised the plan after testing suggestions from a coding-focused agent. Around 700 readers said they use or want a personal agent, and roughly 50% of poll respondents asked how it works in Claude.

Read original

Simple agents

Ben's Bites reports a poll with 996 total votes on personal agent use, and describes personal agents as a folder of files and tools connected to any agentic tool. Headlines include Meta AI's Mac app, Berd by Block, OpenAI pausing model improvements for two weeks, and Ramp launching router.com.

Read original

How Much Memory Does Your Agent Actually Need?

A Hugging Face blog post reports that ALTK-Evolve, which distills guidelines from an agent's own past trajectories and injects them at inference time without weight updates, improves task completion only when the amount of memory is calibrated to the model. Across eight models, strong models benefited from the full guideline set while weaker models did best with curated retrieval.

Read original

Do you use a personal agent?

Ben's Bites is asking readers whether they use agent products as a personal agent, with answers to be revealed in Thursday's post. The newsletter's headlines also cover Grok Bot, new Codex and Claude Code features, Gemini 3.7 Flash, and Stripe's agreement to acquire OpenRouter for more than $7B.

Read original

Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers

Sentence Transformers v6.0 adds a fourth model type, MultiVectorEncoder, for ColBERT-style late interaction retrieval, per a Hugging Face blog post. The post says PyLate and Stanford-NLP ColBERT checkpoints load directly, colpali-engine visual document retrieval models can be used after per-repository configuration, and it describes MaxSim scoring plus index-size tradeoffs.

Read original

Q&A: Rethinking how innovation happens

MIT professor Eugene Fitzgerald discusses his new book "The Invisible Engine: Why Innovation Evades Control," which examines how innovation actually happens and how society should invest in it. The interview covers his strained silicon co-invention at Bell Labs, three categories of research investment, and his argument that innovation is a process rather than an idea.

Read original

Teaching Everyone to Fish for Tokens

Nathan Lambert argues Nvidia is funding open-source model development, reportedly spending $26 billion, so that many companies can build and run their own models rather than buying tokens from Anthropic or OpenAI. He outlines two possible futures for open models and says a long-tail specialization outcome is his most likely.

Read original

A/B test models in production

Together AI describes running A/B experiments at the endpoint level, splitting live traffic among one control and up to 20 variants with fixed percentages. It covers ramping via member updates, measuring platform and product metrics per deployment, and ending tests by promoting a rollout or deleting the experiment.

Read original