mailwal

Dude, where's my context?

The New Stack
October 17, 2026

Dude, where's my context?

Every time an AI agent has to trawl Slack threads, Jira tickets and old pull requests to piece together something a company already knows, the customer pays for that work again. Uvi, an Israeli startup that emerged from stealth on Wednesday with $7.5 million in seed funding from investors including CT Innovations, Cardumen, Mana VC and 91 Ventures, says this repeated context-gathering is quietly inflating the cost of running agents on frontier models.

The firm says in-house agents built on frontier models, connected directly to six company systems, cost roughly eight times more than they needed in internal testing, mostly because of repeated context gathering rather than actual reasoning. Uvi co-founder and CEO Gilad Salinger tells The New Stack that models are rented, but context is owned.

Go deeper: “Developers are paying frontier prices for amnesia”: Uvi wants to stop the agent relearning brain drain

More fresh reads from TNS:

▹Running local AI models on Microsoft’s Surface Laptop Ultra: What we found

▹Hackers hijacked 1,900 GitHub accounts. Then they went after 30,000 repos.

▹Meta ships Muse Spark Open, its answer to China’s best open-weight models

From invoked to proactive: what changes when your incident response agent goes fully autonomous

Most teams talk about agent autonomy as all-or-nothing, but it isn’t. Tune in on October 22 to see how incident response agents progress in production, and what it takes to trust one enough to let it act on its own.

  • How agents move from invoked to background, to proactive
  • What it takes to trust an agent to act on its own
  • What changes for your team at each phase

TOP OF THE STACK

Muse Wonder vs. Claude Fable 5.1: Meta’s new model came closer than I expected

by Jessica Wachtel

Claude Fable 5.1 refused 34 of 50 turns on a webhook project. The first refusal hit an environment variable.

Meta launched Muse Wonder on October 12, about three months after Muse Spark 1.1 opened Meta’s paid Model API. Meta says the Muse Wonder series is strong at personal and professional agent tasks, tops its internal MemoryBench memory test, and, in the Full version, leads coding benchmarks such as DeepSWE...

WHAT ELSE IS NEW?

The tech newsletter that does the math

Cautious Optimism is a daily newsletter for VCs, founders, and engineers, covering technology, business, and power. Every morning you get:

  • Analysis rather than aggregation, so you understand what the news means
  • Where technology and government collide before it hits your roadmap
  • The honest read when the numbers don’t back the hype

FLOW STATE

WEBINAR

No reranker, however capable, can recover a result that retrieval never surfaced in the first place. Watch on-demand to see why teams keep throwing bigger models at a problem that starts earlier in the pipeline.

HOWTO

Catch stale cloud resource ownership before offboarding. Learn queries and policies to reassign infrastructure when team roles change.

WATCH

Agents should hand engineers a fix, the company says, and teams should still check the work.

How did we do today?

ALSO FROM THE IMG FAMILY

More communities worth exploring

Community-powered role and skill-based roadmaps to guide your learning journey in tech.

A modestly upbeat breakdown of what's happening with tech, business and power.

Insights from the brightest minds in data science, machine learning and AI.

Join TNS on your favorite platform

The New Stack is a media platform for the people who build and manage software the world relies on.

© 2026 The New Stack. All rights reserved.
The New Stack 1111 6th Ave Ste 550 PMB 50938 San Diego, CA 92101-5211