Feed aggregator

Article URL: https://thecodersblog.com/julia-language-performance-benchmarks-2026/

Comments URL: https://news.ycombinator.com/item?id=48096609

Points: 1

# Comments: 1

Article URL: https://github.com/uw-syfi/vibe-serve

Comments URL: https://news.ycombinator.com/item?id=48096598

Points: 1

# Comments: 0

Article URL: https://discuss.systems/@ricci/116556373280824179

Comments URL: https://news.ycombinator.com/item?id=48096595

Points: 1

# Comments: 0

Article URL: https://agent-benchmarks.com/

Comments URL: https://news.ycombinator.com/item?id=48096578

Points: 1

# Comments: 0

At one point well before the age of industrialization all furniture was hand crafted so to speak by trained artisans. As time went on they started working together in workshops, had more formal training processes through guilds and perhaps most important saw improved work flows through specialization, improved tooling and the use of ever more sophisticated jigs and templates.

Industrialization took things to another lever. Mastery meant skill in using ever more complicated and industrialized machinery. Profit seeking behavior set the focus on automation, repeatability and perhaps most important reducing the skill necessary to do the job.

Today nearly all furniture is made in factories using not wood but rather sawdust and wood particles glued and pressed together. The process is deskilled, if anything the skilled work is in designing, manufacturing and tuning the machines that make the furniture, not in making furniture itself.

We still teach woodworking in schools, oddly enough though we typically teach it through the lens of using modern machinery when in my opinion when should teach it as art form using traditional hand tools as that type of work is safer, less noisy, cheaper, requires less safe and most important me doesn't have you breathing in airborne particles of sawdust.

This is more of a realization and perhaps a question for you the reader but with the age of AI upon us, will coding go the way of wood working. Will the number of coders become less and less? Will it become deskilled? Will a good coder simply become someone proficient in the use of AI tools? It would seem we're at the dawn of the industrial revolution where the nature of wood working probably started to change.

Comments URL: https://news.ycombinator.com/item?id=48096572

Points: 1

# Comments: 0

Article URL: https://d2l.ai/

Comments URL: https://news.ycombinator.com/item?id=48096560

Points: 1

# Comments: 0

Article URL: https://www.construction-physics.com/p/on-technologies-vs-commodities

Comments URL: https://news.ycombinator.com/item?id=48096549

Points: 1

# Comments: 0

Article URL: https://bloggeek.me/moq-adoption-problem/

Comments URL: https://news.ycombinator.com/item?id=48096546

Points: 2

# Comments: 0

Article URL: https://theaviationist.com/2026/05/10/raf-airdrop-response-suspected-hantavirus-case-on-remote-island/

Comments URL: https://news.ycombinator.com/item?id=48096539

Points: 1

# Comments: 0

Article URL: https://www.theguardian.com/stage/2026/may/11/theatre-streaming-in-person-attendance-national-theatre-nt-live-at-home

Comments URL: https://news.ycombinator.com/item?id=48096536

Points: 1

# Comments: 0

Article URL: https://www.wsj.com/pro/sustainable-business/engineered-carbon-removal-was-supposed-to-be-getting-cheaper-prices-are-going-up-ef97d5db

Comments URL: https://news.ycombinator.com/item?id=48096535

Points: 1

# Comments: 0

Article URL: https://arxiv.org/abs/2605.06544

Comments URL: https://news.ycombinator.com/item?id=48096533

Points: 2

# Comments: 0

Article URL: https://www.incultnito.com/mcp

Comments URL: https://news.ycombinator.com/item?id=48096527

Points: 2

# Comments: 0

Korru is an installable web app catalog with 489 Progressive Web Apps listed.

Get yours listed to increase your visibility and drive some extra traffic at no costs.

Simply drop the link to your PWA. It should follow these rules:

- No harmful content - Your manifest have a "display" property (standalone, fullscreen, ...) - Your manifest have at least 2 icons (192x192 and 512x512) - Your manifest have valid app info (name, URL, start URL) - Make sure to define at least one valid "category" to increase visibility (see https://w3c.github.io/manifest-app-info/#categories-member for an exhaustive list)

You can verify if your app meets installability criterias by going on Google Chrome > Add To Home Screen (if you see a text input that invites to edit the app name, it means you are missing something).

Your app is not a PWA yet? No problem, use either one of these tools to get started:

- https://vite-pwa-org.netlify.app/ (using Vite) - https://web.dev/learn/pwa/workbox (using plain JS or not using Vite as build tool, ask your AI to guide you)

Check the listing at https://korru.app

Comments URL: https://news.ycombinator.com/item?id=48096525

Points: 1

# Comments: 0

Article URL: https://www.bbc.com/news/articles/cp3p5l0nyevo

Comments URL: https://news.ycombinator.com/item?id=48095717

Points: 3

# Comments: 0

Article URL: https://spectrum.ieee.org/mental-health-chatbot-guardrails

Comments URL: https://news.ycombinator.com/item?id=48095713

Points: 1

# Comments: 0

Hello HN!

If you want to connect your agent to a database (say, to build a data analyst chatbot or any kind of agentic app) today you have 2 options: an SQL MCP server or a semantic layer.

SQL MCP is the easiest path to setup, especially if you also have a .md knowledge base which the agent can update. It gets quite messy quickly though, especially if there's many interactions or DB is large. Generated SQL is hard to review if you want to understand where the numbers came from, and related queries can be hard to align and compare.

The natural alternative is a semantic layer, which is an inventory of what data is available/useful (data models) and an interface for querying it using a structured DSL — usually a list of measures, dimensions, filters, with joins etc. handled under the hood.

When we needed a semantic layer at Motley for connecting to our customers' data, we first settled on Cube with custom wiring for multi-tenancy and updating the models on the fly. We quickly hit some limitations which led us to realize existing semantic layers just weren't built for the purpose: they're still a part of the BI world where you want an efficient backend for an essentially static set of human-curated dashboards, whereas agents need to iterate their way to the answer, learning in the process. That's when we built the first version of SLayer, which is now open-source.

Using either SLayer MCP or CLI, agents (and humans) can:

- Explore models, run queries, connect to multiple databases - Edit columns/measures or create new ones - Create custom models from SQL or from a query on other models - Learn from interactions: save and retrieve natural-language memories linked to models, columns or queries, to form a knowledge base

Agents evolve the semantic layer, reuse the results of past interactions, and make fewer mistakes going forward.

A few more features:

- Auto-creation of models from introspecting your DB schema for a warm start - Embeddability — doesn't need a server running - Python client for doing data analysis with dataframes - Schema drift detection and handling - Expressive DSL with compact, natural representations for arbitrarily deep multistage queries, custom aggregations, time shifts, combining metrics from multiple models, and other features that are tricky to get right in raw SQL

On the roadmap: access controls, caching, and more.

Repo: https://github.com/MotleyAI/slayer

Docs: https://motley-slayer.readthedocs.io/en/latest/

Comments URL: https://news.ycombinator.com/item?id=48095686

Points: 2

# Comments: 0

Article URL: https://algorithmicpattern.org/2026/03/11/exploring-8-shaft-weaving/

Comments URL: https://news.ycombinator.com/item?id=48095680

Points: 2

# Comments: 0

Article URL: https://susam.net/advanced-mathematics-pedagogy.html

Comments URL: https://news.ycombinator.com/item?id=48095660

Points: 3

# Comments: 0

Article URL: https://dataengineeringcentral.substack.com/p/the-cognitive-overload-of-ai-development

Comments URL: https://news.ycombinator.com/item?id=48095648

Points: 4

# Comments: 0