Fetching from the wire…
01
02
03
04
05
06
07
08
Agents2026-08-20 · source-backed
Three memory strategies across eight models from 30B to 745B on AppWorld's 585 multi-step tasks. Curated retrieval gave gpt-oss-120b +16.1 percentage points on goal completion for 5% more tokens. DeepSeek-V3.2 needed the full guideline set for +9.5pp at a 78% token cost. GLM-5 gained nothing at all. (Hugging Face) Strong models don't need your memory system, and weak models need the cheap version of it. That inverts how most memory products are priced and positioned.
Each link below shares sources, entities, or timing with this story.
Numbers first, because they're the whole argument. On AppWorld's 168 tasks with DeepSeek-V3.2: ALTK-Evolve hit 89.3% goal completion at 263K tokens per task. ACE hit 80.4% at 634K (IBM Research on HF). Nine points better, 41% of the tokens. On the weaker gpt-oss-120b: 56.0% at...
For about a year, "run your agent locally" meant accepting a model that couldn't reliably call a tool twice in a row. That excuse is gone. Meta Superintelligence Labs published Muse Glimmer today: a 29.6B dense causal transformer, 52 layers, 6,656 hidden dim, with a ~1.8B ViT-...
GPT-5.6 Luna went to $0.20 input / $1.20 output per million tokens on July 30. That's an 80% cut. Terra dropped 20%. Luna's input now undercuts Gemini 3.1 Flash-Lite ($0.25/$1.50) and sits at one-fifth of Claude Haiku 4.5's $1 input. Simon Willison covered the announcement and...
Announced July 27 with Microsoft, IBM, Red Hat, Palantir, CrowdStrike, Cloudflare, Databricks, Hugging Face, LangChain, Nous Research, Reflection AI, Thinking Machines Lab, SpaceXAI and the Linux Foundation. Huang's framing is pointed: during the Hugging Face incident "closed...
$3,054 against $38,370. Same benchmark, better score. Praxist (arXiv 2608.25955, submitted August 26) replaces per-attempt agent memory with a typed evidence graph of findings, plus lane-structured frontiers and agendas, so later attempts inherit validated mechanisms rather th...
Hugging Face published its Summer 2026 State of Open Models report on August 14, and one statistic in it went almost entirely unremarked in the coverage. By July 2026, agents rather than humans became the Hub's primary users. Claude Code alone accounted for 44.4% of all agent...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.