GoKawiil - Tech News

1.

Show HN: Agent-skills-eval – Test whether Agent Skills improve outputs (news.ycombinator.com)

2026-05-07 | get AI Skill Assessment Kit → | tags: agent skills, anthropic, gpt-4

2.

The RAG era is ending for agentic AI — a new compilation-stage knowledge layer is what comes next (venturebeat.com)

2026-05-04 | get AI Knowledge Management Book → | tags: vector databases, pinecone, nexus

3.

Archaeologists Unearth ‘Advanced’ Gold Dental Bridge in Medieval Scottish Grave (gizmodo.com)

2026-05-04 | get Medieval Gold Dental Bridge → | tags: gold dental bridge, medieval scottish grave, dental ligature

4.

The AI scaffolding layer is collapsing. LlamaIndex's CEO explains what survives. (venturebeat.com)

2026-05-01 | get LlamaIndex AI Toolkit → | tags: llamaindex, retrieval-augmented generation, context protocol

5.

The retrieval rebuild: Why hybrid retrieval intent tripled as enterprise RAG programs hit the scale wall (venturebeat.com)

2026-04-29 | get Retrieval-Augmented Generation (RAG) Toolkit → | tags: rag, hybrid retrieval, weaviate

6.

Is fun at work overrated? (feeds.feedburner.com)

2026-04-29 | get Ergonomic Office Chair → | tags: roman galley, medieval serf, textile mill

7.

I Won a Championship That Doesn't Exist (news.ycombinator.com)

2026-04-28 | get Custom Championship Trophy → | tags: llm, poisoning, anthropic

8.

RAG precision tuning can quietly cut retrieval accuracy by 40%, putting agentic pipelines at risk (venturebeat.com)

2026-04-27 | get AI Retrieval Optimization Toolkit → | tags: rag, redis, embedding models

9.

Monitoring LLM behavior: Drift, retries, and refusal patterns (venturebeat.com)

2026-04-25 | get AI Behavior Monitoring Toolkit → | tags: ai evaluation stack, generative ai, hallucination

10.

Closure of China’s influential journal ranking leaves academics reeling — what will take its place? (feeds.nature.com)

2026-04-24 | by Basu | get Academic Journal Impact Kit → | tags: cas journal ranking, chinese academy of sciences, xinrui scholar

11.

Evaluating large language models for accuracy incentivizes hallucinations (feeds.nature.com)

2026-04-22 | by Kalai | get AI Language Model Debugger → | tags: large language models, hallucinations, open-rubric evaluations

12.

Watch the Lego ‘Project Hail Mary’ Set (Almost) Go to Space (gizmodo.com)

2026-04-21 | get LEGO NASA Apollo Saturn V → | tags: lego, project hail mary, guinness world record

13.

Duolingo was evaluating its workers’ AI use. Workers pushed back. (feeds.feedburner.com)

2026-04-15 | get Duolingo Language Learning Kit → | tags: duolingo, luis von ahn, performance reviews

14.

Show HN: Continual Learning with .md (news.ycombinator.com)

2026-04-13 | get Deep Learning Notebook Kit → | tags: show hn, memory filesystem, ai agents

15.

Scientists Used Medieval Poems and Trees to Uncover a 13th-Century Solar Surge (gizmodo.com)

2026-04-10 | get Solar Power Bank → | tags: medieval poems, solar surge, northern lights

16.

Wit, unker, Git: The lost medieval pronouns of English intimacy (news.ycombinator.com)

2026-04-09 | tags: wit, medieval pronouns, english language

17.

A Digital Compute-in-Memory Architecture for NFA Evaluation (news.ycombinator.com)

2026-04-07 | tags: compute-in-memory, nfa, architecture

18.

Smart people recognize each other – science proves it (news.ycombinator.com)

2026-04-06 | by Comuniq Team | get IQ Testing Kit → | tags: intelligence, christoph heine, mozzapp

19.

How to deal with a passive-aggressive colleague (feeds.feedburner.com)

2026-04-01 | get Dealing with Passive-Aggressive Behavior Book → | tags: passive-aggressive, interpersonal interactions, medieval societies

20.

General scales unlock AI evaluation with explanatory and predictive power (feeds.nature.com)

2026-04-01 | by Zhou | get AI Evaluation Toolkit → | tags: ai evaluation, general scales, cognitive abilities

21.

The story of Britain's oldest sweet, the Pontefract Cake (2019) (news.ycombinator.com)

2026-03-31 | get Pontefract Cake Candy → | tags: pontefract castle, liquorice, pontefract cakes

22.

Red Rooms makes online poker as thrilling as its serial killer (theverge.com)

2026-03-29 | by Terrence O'Brien | get Poker Night Set → | tags: red rooms, dark web, pascal plante

23.

Duolingo’s CEO Uses a Secret Test to Evaluate Job Candidates — Before They Even Step into the Interview (feeds.feedburner.com)

2026-03-27 | by Sherin Shibu | get Duolingo Language Learning App → | tags: duolingo, luis von ahn, taxi evaluation

24.

Chroma Context-1: Training a Self-Editing Search Agent (news.ycombinator.com)

2026-03-26 | get AI Self-Editing Tool → | tags: chroma, retrieval-augmented-generation, large language model

25.

Show HN: Claude skill that evaluates B2B vendors by talking to their AI agents (news.ycombinator.com)

2026-03-26 | get AI Vendor Evaluation Toolkit → | tags: claude, buyer eval, salespeak api

26.

Gerard of Cremona (news.ycombinator.com)

2026-03-26 | get Gerard of Cremona Translation Kit → | tags: gerard of cremona, toledo school of translators, ptolemy almagest

27.

I built an AI receptionist for a mechanic shop (news.ycombinator.com)

2026-03-23 | get AI Receptionist for Mechanics → | tags: ai receptionist, retrieval-augmented generation, large language model

28.

Our whole way of thinking about leadership is a century out of date (feeds.feedburner.com)

2026-03-23 | get Leadership Books for Modern Leaders → | tags: leadership, employee motivation, management practices

29.

Tech Employees Are Reportedly Being Evaluated by How Fast They Burn Through LLM Tokens (gizmodo.com)

2026-03-22 | get Token Counting Keyboard → | tags: llm tokens, tech employees, evaluation

30.

VisiCalc Reconstructed (news.ycombinator.com)

2026-03-17 | by Serge Zaitsev | get VisiCalc Reconstructed Kit → | tags: visicalc, dan bricklin, apple ii