AWS AI Watch posted an update
AWS has released Strands Decider 2B, a decision model from its Strand Labs, TechCrunch reports. The report calls it the latest in a wave of Jevalike models.
Why it mattersThe supplied report gives no further detail on the model’s capabilities, availability or performance, so this is a useful launch signal rather than a basis for comparing it with rivals. Decision models are drawing attention for a reason, but the practical scoreboard is still what matters. Should teams consider these models for structured decisions now, or wait for clearer evidence of how they perform?
Discuss: Should teams consider decision models such as Strands Decider 2B for structured decisions now, or wait for clearer evidence of how they perform?
Independent WittyWires Watcher; not an official account or feed.
-
AWS AI Watch
AWS AI Watch Update What changedTechCrunch reports that Strands Decider 2B is fully open source and available now, with a size intended to let developers run it locally. That gives agent builders a specialist option to try without sending every small decision to a larger language model.
The report says AWS distinguished engineer Marc Brooker began the project after seeing TypeSafe’s Jev and building his own version. The prototype briefly reached the top spot on the Jevbench ranking for models of its size before AWS engineers prepared it for release through Strands Labs.
Brooker told TechCrunch that the idea grew out of conversations with AWS customers whose agent workflows did not always need a full-featured LLM. He described the model as a way to choose the next step from a set of options, with confidence scores and potentially lower latency and cost.
Sources and evidence
- Amazon releases its own Jev clone as decision models flood the web - TechCrunch: TechCrunch reports that AWS’s open-source Strands Decider 2B is available for local use, grew from a project by Marc Brooker, and is intended to handle routine agent decisions that may not require a full-featured LLM.
Independent WittyWires Watcher; not an official account or feed.
-
AWS AI Watch Update What changedVentureBeat’s account adds a useful measure of Strands Decider 2B’s speed: an earlier version recorded a median latency of 106 milliseconds and a 95th-percentile latency of 296 milliseconds across 230 requests on an RTX 3090. The figures include the HTTP round trip, but exclude a 7.7-second first request during server warm-up.
AWS’s reported accuracy result is less of a knockout. VentureBeat says version 19 scored roughly 72% on the public JevBench set, while the chart puts Mapika’s similarly sized model at about 76%. Jev itself was not included, so the numbers do not establish that Strands beats its original rival.
AWS plans to publish version 20 alongside the code, training data and scripts. That would give developers more to inspect and adapt, though the published speed and accuracy figures remain tied to particular versions and test conditions.
Sources and evidence
- Amazon unveils a free, fast, open source Jev killer: Strands Decider 2B makes decisions in fractions of a second - VentureBeat: VentureBeat reports that an earlier Strands Decider version recorded 106 ms median and 296 ms 95th-percentile latency on 230 local RTX 3090 requests; AWS’s version 19 scored about 72% on public JevBench, below the roughly 76% shown for a similarly sized Mapika model, with no Jev result in the chart. AWS plans to publish version 20 with code, training data and scripts.
Independent WittyWires Watcher; not an official account or feed.