The model that decides instead of chatting. Tech & AI Weekly by Eli, October 02 2026
Jev and Strands Decider launch a new kind of decision model, three frontier labs ship in days, and prices fall across the board.
Tag: newsletter
-
-
Same model, 5x the bill, depending on the harness. Tech & AI Weekly by Eli, September 18 2026
Berkeley's harness-tax study found the same model costs up to 5x more depending on the harness. Plus: the best coding agent fails 60% on unseen code, and GitHub rewrites the Copilot runtime in Rust using Copilot.
-
Can AI build your agent? A benchmark says 23.9%. Tech & AI Weekly by Eli, September 11 2026
Sierra's benchmark asked coding agents to build a working AI agent. The best passed 23.9%, and one sentence about architecture took another from 31% to 67%.
-
The harness beat the reasoning dial. Tech & AI Weekly by Eli, September 4 2026
The harness added 36 points to GPT-6 Astra's benchmark. Also: what agent memory should throw away, DoorDash's 130K agent tasks, Kiro Crew goes open source, and pnpm 12 in Rust.
-
AI agents now control lab equipment. Tech & AI Weekly by Eli, August 29 2026
Anthropic released a spec for AI agents to control physical lab equipment. Also: self-improving AI, AWS AgentCore Evaluations, Meta's custom silicon, and a $40k hackathon.
-
Memory Is Having a Moment. Tech & AI Weekly by Eli, August 14 2026
Two weeks of AI in one edition: context engineering from 35% to 98%, Meta's local 30B agent model, a shared plugin standard backed by five companies, and Anthropic's dream memory.
-
Stateless MCP, 80% price cuts, and 37 agent projects in one day. Tech & AI Weekly by Eli, July 31 2026
Stateless MCP lands, GPT-5.6 drops 80% in price, Claude Opus 5 ships, and 151 builders built 37 agent projects in one day.
-
The model isn't the bottleneck anymore. Tech & AI Weekly by Eli, July 24 2026
Agent architecture over model choice: the context layer, converging agent platforms, Anthropic's $1.5B settlement, Kimi K3, and AI agent memory types.
-
Every agent decision needs a receipt. Tech & AI Weekly by Eli, July 17 2026
Stripe benchmarked where agents fail, agents outspending humans, and the evidence-packet future of agent observability.
-
I watched a RAG pipeline poison its own memory. Tech & AI Weekly by Eli, July 10 2026
This week: a RAG pipeline that poisoned its own vector store, GitHub's AI agent tricked into leaking private repos, GPT-5.6, and what I'm digging into next: graph-based memory for agents.
-
Fable 5 returns, agent memory levels up. Tech & AI Weekly by Eli, July 3 2026
Claude Fable 5 returns to Bedrock, Sonnet 5 lands on AWS, and AgentCore memory gets metadata filtering. This week in tech and AI.
-
A fake bug report can hijack your coding agent. Tech & AI Weekly by Eli, June 26 2026
This week: AgentJacking hijacks Claude Code, Cursor, and Codex through a fake Sentry bug report, new research on why models confuse trusted and untrusted text, Strands chaos testing, AWS Blocks, and Lambda MicroVMs.
-
Strands cut agent costs in half, and I published a book — Tech & AI Weekly, June 19 2026
This week: I published my book on AI agents that don't hallucinate or waste tokens, Strands cut agent costs in half, GLM-5.2 open weights, and the agent launches from AWS Summit New York.
-
A frontier model got pulled in 72 hours. Tech & AI Weekly by Eli, June 13 2026
Welcome to my very first newsletter!
