Zils

Custom decision models. Built on Bittensor

[Zils @zils_ai]

Please wait until official announcements surrounding Zils infrastructure.

Zils is not subnet 27 or 86.

[Zils @zils_ai]

@ShizzyUnchained @LamidaGlobal @const_reborn Yea right. We're not reacting to this at all. Haha.

[Erik Spock Gafni (hiring!) @EGafni]

New Jev on OpenRouter!

[Zils @zils_ai]

Zils vs JEV

DOOM Benchmark.

[Tseu Tseu - τao @tseutseutao]

$TAO - Chain upgrade!

Bittensor is speeding things up: launching new subnets is now cheaper, but their immunity is slashed to just 60 days (previously 120).

Great update because it quickly flushes out dead weight, ensuring only active, top-tier projects access the network.

Survival of the fittest at its finest.

[Raleigh, CA | OOO @Raleigh_CA]

Make better decisions. @zils_ai

$tao

[Zils @zils_ai]

https://t.co/xR1TJ347zZ

[Zils @zils_ai]

New in Zils SDK 0.2.0: ranking.

Give Zils 2–10 options and tell it what matters, like which support action best addresses a customer’s issue.

Get an ordered list with relative scores. Available in Python and TypeScript. Experimental.

https://t.co/grnEJolNP5

[Zils @zils_ai]

New in Zils SDK 0.2.0: ranking.

Give Zils 2–10 options and tell it what matters, like which support action best addresses a customer’s issue.

Get an ordered list with relative scores. Available in Python and TypeScript. Experimental.

https://t.co/grnEJolNP5

[Florian S @airesearch12]

Official JevBench results:

Microsoft-Decision-1 scores #6 in its peer group of API provided decision models.

Compared with Jev it performs strong on many typical use cases, most notably on Recruiting, Risk assessment, Gaming, Advertising, Science and Moderation.

It's also the strongest API provided model in the top 10 in mixed-language tasks.

In our headline ranking for API offered models Jev superseeds it on #4 and Sage leads on #1.

Please be aware that JevBench seperates the leaderboards of
- API offerered models such as Microsoft-Decision-1
(found here: https://t.co/iMKfigomA8) and
- open weights models
(found here: https://t.co/vK5MhQbRws),
because speed and cost can only be scored in a fair way within these seperate peer groups.

In a mixed leaderboard of open and API hosted models it lands #12 on the composite score.

It's a good model, and certainly will find its customer base, given Microsofts strong position in enterprise compliant cloud offerings.

Congrats @Microsoft!

[Zils @zils_ai]

Your model > Their model.

[Zils @zils_ai]

These are real results.

[Zils @zils_ai]

The race to build better decision models is fun to watch.

[Zils @zils_ai]

@gavinzaentz @opentensor

[Zils @zils_ai]

Custom decisions models. built on @opentensor

https://t.co/DED8EFBpeC

$tao #jev

[Danny Herrmann @MuffinDannyH]

Custom decision models are coming to Bittensor

Zils takes your examples and the right answers, then trains a small model that can make specific calls sorting requests, flagging problems, scoring matches. It doesn’t chat. It returns a typed decision and a confidence score, Jev-style.

It’s built on OpenTensor, so it sits inside the bittensor:native ecosystem. If you want a decision layer trained on your own data without spinning up a big model, this is that direction.

[Zils @zils_ai]

distribute.

$tao

[Zils @zils_ai]

Open-source decision models vs. @typesafeai’s Jev.

$TAO

[Zils @zils_ai]

@mweingarten7 @Blockchain_Dame Sub $2 is good. Down due to BTC

[Zils @zils_ai]

@RNR_0 The*