such a (visually) beautiful blogpost.

The easiest way to strip complexity is to expose simple tools to an agent model like SID-1 that can use them well. It makes more of an effort for hard questions, and little effort for easy ones.

(found of sid.ai so obv biased)

SID-1 co-author here: was a lot of fun writing it. want to chat? just firstname at domain.

yup! email sent!

> "compatible" instead of "comparable."

It boggles my mind how you can train a frontier model but not write a tweet without an obvious typo.

The people training the model are almost certainly not the same ones writing tweets. I don't know why that is mind boggling. We all make typos, at least the humans among us do.

let's see your grammatical correct tweet in chinese.

Accurate reflection of Alibaba's cloud platform as a whole. I've never seen more misused terminology and strange word choices than when testing out their cloud dashboard.

This is egregious for a model announcement though, I agree with you 100%.

Now you can be sure they write their announcements by hand. Doesn't really matter, does it?

It's OK because I'm not prompting the person who tweeted for my usecases.

mistakes are at the moment a signature quality of human written texts, enjoy them

i'll take that 100% over llm slop.

at the risk of upsetting a lot of people mentioning this but like are you really surprised?

if youre going to use ai for everything youre gonna start losing your edge as you focus less and less on what youre doing and this isnt me just talking out my ass, like... the front page here is peppered with study after study and blogpost after blogpost about how its overuse can come to the detriment of one's own abilities and skills.

coca cola had the ad with the magical truck that changed its design, shape and amount of tires it had and if nobody noticed that before releasing it then im not sure why anyone might think that the people peddling the LLMs would somehow be immune to this phenomenon

This is the sort of unmitigated pedantry thats the real problem. Everyone makes typos and errors of this nature. Feymann and Hemmingway both did. You deliberately chose this level of error multiple times when you chose to not put an apostrophe in youre and failed to capitalize proper nouns

Come off that high horse

i literally have no idea what you're talking about my dude/gal and/or pal.

i just dont have autocorrect turned on; chill.

does it support fts/vector on edges of the graph?

Yes you can put vectors, full text data, secondary and range indexes on both nodes and edges.

are you a maintainer on npm?

lol thankfully no. My GitHub is in bio

We think this is a pretty sad day for research: Some context about Chroma's model. https://x.com/maxrumpf/status/2037365748973384154?s=20

can you share actual links for your published research and theirs .

This is the tech report for a model I helped work on. I'm biased, but it turned out very well.

We essentially let the model learn to retrieve like a human would: Make a first search, read the results, and then make another. This lets the model be vastly better than pre-programmed pipelines. We test this extensively and compare against implementing this with API models (like Sonnet 4.5 and GPT-5.1). SID-1 compares favorably.

Happy to answer any questions or get feedback. First and foremost: Enjoy the read. It's much more detailed than most tech reports.

This comment section is scary. Hacker news advocating FOR nanny technology?!