Sapient Intelligence releases HRM-Text, a 1B-parameter reasoning model trained on 40B structured tokens that reaches competitive performance with one-thousandth the data volume of comparable systems

Full training finished in one day for under $1,000.

Original post

OPAD#867Alexander Doria|@DORIALEXANDER

Very happy to see SYNTH continuing to power innovative model research.

4:46 PM · May 18, 2026 View on X

QUOTE POSTAD#867Alexander Doria|@DORIALEXANDER

Very happy to see SYNTH continuing to power innovative model research.

11:46 PM · May 18, 2026 · 6.6K Views

REPLYAD#867Alexander Doria|@DORIALEXANDER

from their documented data pipelines https://github.com/sapientinc/data_io/tree/main (seems to be the leading source along with OpenThouths and OpenMathInstruct-2)

ADAlexander Doria@Dorialexander

Very happy to see SYNTH continuing to power innovative model research.

11:46 PM · May 18, 2026 · 6.6K Views

12:52 AM · May 19, 2026 · 518 Views

QUOTE POSTVK#1450Vikash Kumar|@VIKASHPLUS

SCALING ISN’T EVERYTHING

Another tiny model breaking the rule. -trained on less than 1/1000th of the data - can be trained in a single day with <1000 USD

Human knowledge base ca be compressed & retrieved much tighter than LLMs do today.

12:06 AM · May 19, 2026 · 6.3K Views