Kappa90

Thank you, if you happen to try it out or have ideas, feel free to contact me at: em at dinobase dot ai

Right now schema changes create new columns, I’m working on reconciling old columns, which right now are not dropped.

The annotation/semantic layer agent creates a new description of the schema on sync, which represents the current state, but that includes stale columns as of today, data is not dropped.

I’ll implement automated schema migrations in the next week or so!

It's not explicitly stated in the benchmarks README, good catch.

80% of the benchmark questions are aggregations, 16% are multi-hop, 4% are lookups/subqueries.

Multi-hop is where LLMs struggle the most (hallucinations, partial answers), and aggregations is where you get the most token efficiency, since you skip on pagination which you need with APIs/MCPs that don't provide filters.

DuckDB exposes Postgres SQL, and most coding LLMs have been trained on that.

Of the small models I tested, Qwen 3.5 is the clear winner. Going to larger LLMs, Sonnet and Opus lead the charts.

It's an experimental benchmark, I couldn't find any off-the-shelf benchmarks to use this with. There's Spider 2.0 but it's for text-to-SQL. I'm planning to run this [1] next but it's quite expensive.

There's 75 questions, divided in 5 use case groups: revenue ops, e-commerce, knowledge bases, devops, support.

I then generated a synthetic dataset with data mimicking APIs ranging from Stripe to Hubspot to Shopify to Zendesk etc..

I expose all the data through Dinobase vs. having one MCP per source e.g. one MCP for Stripe data, one MCP for Hubspot data etc.

I tested this with 11 models, ranging from Kimi 2.5 to Claude Opus 4.6.

Finally there's an LLM-as-a-judge that decides if the answer is correct, and I log latency and tokens.

[1] https://arxiv.org/abs/2510.02938

A podcast on the history of the “Majority World” - that is Africa, Asia, the Middle East, Oceania, Latin America and the indigenous people around the world - from a decolonisation point of view.

I just published the first episodes today and have zero listeners or subscribers, so it can only grow from here!

https://historyofthemajorityworld.com

Spotify: https://open.spotify.com/show/4qJh2jNwMvWcLP1J1EMXxr?si=dcc7...

Apple Podcasts: https://podcasts.apple.com/rw/podcast/history-of-the-majorit...

Hey, one of the devs working on PostHog AI here.

The main reason why we advocate for a single-loop is because subagents suffer from the telephone game problem: context is lost when the interface is just an agent-to-agent prompt.

We are still working on subagents for parallelization, but if you can stick to the main loop, everything works much better.

Used Copilot to write a user auth migration script. It silently reset 2FA settings for ~3k users with OAuth accounts because it didn't handle NULL vs empty string edge cases in our legacy DB schema. Classic "garbage in, garbage out" situation.

Found out two weeks later when angry users couldn't log in during peak hours. Damage: 4 hours of downtime, one very grumpy security team, and a new "no AI for auth code" policy.

If you want to see an LLM tackling unit testing, check https://www.codebeaver.ai

Disclaimer: I’m the developer behind CodeBeaver

There seems to be a peak in traffic I guess due to HN, apologies! If you have any further problems it would be really helpful if you'd let me know at [email protected]

If you're looking for a replacement for Artifact (and for news apps in general), you should check out https://tailor.news

It aggregates the news from thousands of newspapers, youtube channels and podcasts, then serves you a summarized digestible version, as a feed and as a personalized podcast, using LLM models.

You can also ask to clarify or explain the news, and there's a new function to ask if an article's claims are supported by other sources, to avoid reading biased or opinionated information.

Disclaimer: I'm one of the founders of Tailor

An app that aggregates the news from websites, blogs, YouTube channels and podcasts, and generate easily digestible summaries, along with a small podcast version so you can stay informed in an easy stress-free way.

Right now I’m working on including automatic fact checking and insights on how each source might be opinionated vs. reporting just the facts.

https://usetailor.com

Indeed, there is no other tool out there automatically linking documents for you, as far as we know.

The idea is that Saga helps you resurface connections and ideas without having to do the manual work yourself.

This allows for a more serendipitous discovery of knowledge while you're crafting content or researching a topic.

Areas where we see great promise are: - analyzing interviews and notes for product and user research - automatically generate company or support wikis from docs - discover insights while writing meeting/team notes and documentation

Currently beta testing realtime collaborative editing and we'll start pushing towards integrating with other tools after that.

Checkout Saga [0], we've been building this for over a year exactly to fix the "I can't find anything" problem. Any feedback appreciated!

[0] https://saga.so

We're developing Saga [0] and we have many users using it for Zettelkasten, although it's not our main value proposition.

Why: Saga automatically links pages one to another, so it builds your wiki/knowledge system automatically for you.

You can also group pages in "Collections", which are smart tags similar to the Zettelkasten tagging method, which allows users to easily recollect and find notes.

I welcome anybody to try Saga for Zettelkasten and give us feedback on how we can make it a better tool for this use case!

[0] https://saga.so

We did look into editor.js and the API seems not as advanced as Slate's, mostly because Slate tries to replicate the DOM's behavior with Nodes and Ranges, so you can make edits in a very fine grained way.

If you're going for a new text editor, I'd start with Tiptap and try to check how to do advanced custom stuff with Prosemirror. Maybe if Tiptap 2 was out a year ago, we would have started with that.

For collaborative editing, definitely check out https://yjs.dev

I know it sounds like tech debt...and it is. But we're to a point where we could potentially be able to integrate those extensions back into the core library and our slate-saga, so it's eventually paying back.

We really needed extensive text manipulation, so starting from Slate gave us a considerable initial boost, but congrats on building your own parser!

Congrats to you and if you try out Saga, let us know about it :)

Have been building https://saga.so with Slate for the last 12 months.

Can confirm it was a bumpy ride, but it also gave back a lot. The main reasons for using Slate over Prosemirror were the almost complete API for managing and editing a block based page, and the fact that it's written in Typescript (although partial types support is a recent addition).

We still have quite a few Slate-related bugs, and the size of our extension code to cover for slate bugs/omissions or to extend the behavior in general is now many thousands of lines long, but wouldn't have chosen anything else.

We tried Prosemirror at the beginning and it was very hard to get into. We checked again when TipTap came out (which is a wrapper of Prosemirror), but all our advanced custom logics would have had to be rewritten in Prosemirror so we abandoned the idea very easily. But we support the team behind Tiptap on another open source project, Hocuspocus, which is a client/server wrapper for Yjs, a library for collaboration with a focus on text editors.

In the end, I have PTSD from Slate, but also, we couldn't have done it without it, so thanks Ian if you're reading this!

https://tiptap.dev

https://hocuspocus.dev

https://yjs.dev

* my first comment on HN after years of lurking!