WeWorkBuddy

Source-backed discovery

New Term Radar

Discover names and concepts appearing in public sources, with dated evidence, source coverage and comparable growth.

Saved terms stay in this browser and do not sync to your account. Source collection continues on the server without this page being open.

Collection coverage · Comparable windowsCurrent / previous observed days 7 / 7

Counts use complete UTC days. First observed means first seen by this collection, not when a term was coined.

Current window：2026-10-31 → 2026-11-07 (end excluded) · History 19 days

Observed source coverage by seven-day window
SourceCurrent daysPrevious daysLast success
arXiv65Nov 7, 2026, 12:45 AM UTC
arXiv74Nov 7, 2026, 5:30 AM UTC
Ask HN75Nov 7, 2026, 4:30 PM UTC
Ask HN75Nov 7, 2026, 4:30 PM UTC
Ask HN75Nov 7, 2026, 4:45 PM UTC
Ask HN75Nov 7, 2026, 4:45 PM UTC
GitHub75Nov 7, 2026, 1:15 PM UTC
GitHub Issues75Nov 7, 2026, 4:15 PM UTC
GitHub Releases73Nov 7, 2026, 12:45 PM UTC
GitHub75Nov 7, 2026, 2:45 PM UTC
GitHub Issues75Nov 7, 2026, 5:15 PM UTC
GitHub Releases75Nov 7, 2026, 5:15 PM UTC
GitHub75Nov 7, 2026, 2:45 PM UTC
GitHub Issues75Nov 7, 2026, 5:30 PM UTC
GitHub Releases75Nov 7, 2026, 5:15 PM UTC
GitHub Discovery20Nov 7, 2026, 4:45 PM UTC
GitHub Trending75Nov 7, 2026, 8:00 PM UTC
Google74Nov 7, 2026, 8:45 AM UTC
Hugging Face74Nov 7, 2026, 8:45 AM UTC
Hugging Face Spaces20Nov 7, 2026, 4:30 PM UTC
Hacker News75Nov 7, 2026, 8:00 PM UTC
Hacker News75Nov 7, 2026, 4:45 PM UTC
Hacker News75Nov 7, 2026, 4:45 PM UTC
Hacker News20Nov 7, 2026, 4:45 PM UTC
Show HN20Nov 7, 2026, 4:45 PM UTC
MIT News74Nov 7, 2026, 5:45 PM UTC
OpenAI75Nov 7, 2026, 11:45 AM UTC
Product Hunt75Nov 7, 2026, 8:00 PM UTC
量子位65Nov 6, 2026, 7:00 PM UTC
OpenRouter20Nov 7, 2026, 10:05 PM UTC
GitHub Trending77Nov 6, 2026, 1:15 PM UTC
Hugging Face Models20Nov 7, 2026, 10:05 PM UTC
HF Daily Papers20Nov 7, 2026, 10:05 PM UTC
OpenRouter20Nov 7, 2026, 10:05 PM UTC
Product Hunt77Nov 6, 2026, 1:15 PM UTC
SEC EDGAR75Nov 7, 2026, 10:45 AM UTC
Sequoia Capital74Nov 7, 2026, 6:45 AM UTC
Simon Willison20Nov 7, 2026, 3:30 PM UTC
TechCrunch75Nov 7, 2026, 9:45 PM UTC
Contracts Finder75Nov 7, 2026, 8:15 PM UTC
V2EX75Nov 7, 2026, 9:45 PM UTC
  • Counts describe monitored public sources, not the whole web or search demand.
Reset

1,996 matching termsLast snapshot Nov 7, 2026, 10:17 PM UTC

Seven-day figures use the complete UTC window above. Priority is a research triage score, not search volume, market size or a probability of success.

  1. Named entitySteady

    PerMIT

    arXiv:2610.28987v1 Announce Type: new Abstract: Persistent memory is a largely undefended surface for injection and poisoning, and the same risk limits memory sharing among agents. We present PerMIT, a memory architecture with provable integrity guarantees under an explicit trust assumption: only user-typed inputs and values confirmed at a gate are trusted.

    First observed Oct 22, 2026 · arXiv

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  2. ConceptSteady

    MSA

    arXiv:2610.30344v1 Announce Type: new Abstract: Training Arabic large language models faces challenges from noisy web data, dialectal variation, and the high cost of continual pretraining (CPT). We introduce AQL-Lite (AQL: Arabic Quality Language), a time- and resource-efficient framework for adapting a multilingual LLM to Modern Standard Arabic (MSA). AQL-L

    First observed Oct 24, 2026 · arXiv

    7d mentions
    0 previous 1
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  3. Named entitySteady

    Secondhand Stress

    First observed Oct 19, 2026 · arXiv

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  4. Named entitySteady

    Aw-1

    First observed Oct 21, 2026 · Hacker News

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  5. Named entitySteady

    TauIndianBankBench

    arXiv:2610.30161v1 Announce Type: new Abstract: Many Indian banks serve customers through FAQ pages and scripted chatbots. Assistants based on language models could respond faster and carry out requests such as blocking a card, but only if they give correct information and follow the bank's rules. These rules prescribe a procedure, a set of required steps, s

    First observed Oct 24, 2026 · arXiv

    7d mentions
    0 previous 1
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  6. Named entitySteady

    FlashMap

    First observed Oct 20, 2026 · arXiv

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  7. Named entitySteady

    StoreBench

    First observed Oct 9, 2026 · arXiv

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  8. Named entitySteady

    HeRE

    First observed Oct 19, 2026 · arXiv

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  9. Named entitySteady

    Higherlevel

    First observed Oct 10, 2026 · Hacker News

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  10. Named entitySteady

    Vibetown

    First observed Oct 19, 2026 · Hacker News

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  11. Named entitySteady

    HERO

    First observed Oct 16, 2026 · arXiv

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  12. Named entitySteady

    Behind Aggregate Scores

    arXiv:2610.30512v1 Announce Type: new Abstract: LLM judges are used to determine which of two answers is better. Trusting these verdicts requires knowing how repeatable they are and how much they depend on the judge's instructions. We show that similar aggregate scores can conceal substantial changes in individual verdicts, both when the same setup is repeat

    First observed Oct 24, 2026 · arXiv

    7d mentions
    0 previous 1
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  13. Named entitySteady

    H2DF

    arXiv:2610.26864v1 Announce Type: new Abstract: Gradient ascent (GA) is a simple language-model unlearning baseline, but it continues increasing forget loss after useful forgetting has occurred. This unbounded pressure can damage retained utility and make forgotten examples abnormally high-loss. We introduce H2DF, a calibrated target-band objective that appl

    First observed Oct 22, 2026 · arXiv

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  14. Named entitySteady

    AuditKIT

    First observed Oct 19, 2026 · arXiv

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  15. Named entitySteady

    SteerSearch

    First observed Oct 20, 2026 · arXiv

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  16. Named entitySteady

    Algebras Harness

    First observed Oct 20, 2026 · Hacker News

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  17. Named entitySteady

    AutoIndexer

    First observed Oct 12, 2026 · arXiv

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  18. Named entitySteady

    HedgePick

    First observed Oct 18, 2026 · Hacker News

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  19. Named entitySteady

    Tune-Up

    First observed Oct 11, 2026 · Hacker News

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  20. Named entitySteady

    FusionEval

    arXiv:2610.30162v1 Announce Type: new Abstract: Model fusion aims to integrate the capabilities of multi-expert models into a single model. Existing evaluations offer limited coverage of reasoning with long chains of thought and tool use, while strong average performance can mask substantial losses in individual expert capabilities. We introduce FusionEval,

    First observed Oct 24, 2026 · arXiv

    7d mentions
    0 previous 1
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  21. Named entitySteady

    GardenBench

    First observed Oct 20, 2026 · arXiv

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  22. Named entitySteady

    Ex-Nvidia-turned-VC Amulya Vishwanath

    It’s the moment everyone is waiting for — the ChatGPT moment for robotics, Amulya Vishwanath explained to TechCrunch’s Equity.

    First observed Oct 20, 2026 · TechCrunch

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  23. Named entitySteady

    Virgil

    First observed Oct 10, 2026 · Hacker News

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  24. Named entitySteady

    HiRO-ACEv2

    First observed Oct 15, 2026 · Hugging Face

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  25. Named entitySteady

    AQL-Lite

    arXiv:2610.30344v1 Announce Type: new Abstract: Training Arabic large language models faces challenges from noisy web data, dialectal variation, and the high cost of continual pretraining (CPT). We introduce AQL-Lite (AQL: Arabic Quality Language), a time- and resource-efficient framework for adapting a multilingual LLM to Modern Standard Arabic (MSA). AQL-L

    First observed Oct 24, 2026 · arXiv

    7d mentions
    0 previous 1
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  26. Named entitySteady

    Evaluating Compressed Memory

    First observed Oct 16, 2026 · arXiv

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  27. Named entitySteady

    AtomSD

    arXiv:2610.26926v1 Announce Type: new Abstract: Large language models (LLMs) possess broad factual knowledge and strong reasoning capabilities, but solving complex tasks also requires procedural knowledge about how to act. Existing approaches often represent procedural knowledge through trajectories or bundled skills, limiting flexible reuse across interacti

    First observed Oct 22, 2026 · arXiv

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  28. Named entitySteady

    Cognitive Thermometers

    First observed Oct 9, 2026 · arXiv

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  29. Named entitySteady

    Route-and-Generate

    arXiv:2610.30351v1 Announce Type: new Abstract: Large language models often apply complex reasoning indiscriminately, leading to overthinking on simple tasks and underthinking on harder ones. We present Route-and-Generate (Rouge), a hierarchical training framework that enables LLMs to adaptively decide when and how much reasoning is required for each input.

    First observed Oct 23, 2026 · arXiv

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100

  30. Named entitySteady

    KIRA

    arXiv:2610.28840v1 Announce Type: new Abstract: Early-grade reading screening is critical for identifying children at risk of reading difficulty. Existing AI-based screeners are often limited in the scope of their analyses and evaluation metrics, or are proprietary systems that lack transparent model specifications and evaluation. We present KIRA, a dual-pat

    First observed Oct 23, 2026 · arXiv

    7d mentions
    0 previous 0
    7d sources
    0
    7d growth
    Not comparable
    Priority
    9 / 100