◈Bluesky50
YHacker News50
XX / Twitter50
listening to
Jev
150
mentions
tracked
tracked
net sentiment
+25%
48 positive
92 neutral
10 negative
volume & sentiment over time
Sep 25, 2026 · Daily
sources
most discussed
decision / models
active days
1
what people keep raising
- decision / models 36
- built 15
- models 9
- model 7
- open-source / alternative 4
- performance 3
mentions
Showing 1–4 of 4 mentions
-
◈ Bluesky 1w ▲ 0 negative decision / modelsInteresting use of Jev, seems to me, isnt one fast, cheap decision — it’s the ability to fan out on many decisions in parallel. Eg intent, relevance, progress, routing, tool choice, etc — evaluated in parallel, forming a decision matrix that deterministic harness code resolves into the next action. Interesting use of Jev, seems to me, isnt one fast, cheap decision — it’s the ability to fan out on many decisions in parallel. Eg intent, relevance, progress, routing, tool choice, etc — evaluated in parallel, forming a decision matrix that deterministic harness code resolves into the next action.view source ↗
-
◈ Bluesky 1w ▲ 3 negativelike, you could slap jev into the loop to just be _alerting_ but not blocking regarding this sort of behavior and get quicker human-in-the-loop interventions than what they are exhibiting. alignment is one thing, but this is just lack of caring. like, you could slap jev into the loop to just be _alerting_ but not blocking regarding this sort of behavior and get quicker human-in-the-loop interventions than what they are exhibiting. alignment is one thing, but this is just lack of caring.view source ↗
-
◈ Bluesky 1w ▲ 0 negativeJev is not very good at niche topics. Jev is not very good at niche topics.view source ↗
-
◈ Bluesky 1w ▲ 11 negative models‘TypeSafe is betting that many routine tasks now handed to expensive general-purpose models can instead be performed by cheaper, more specialised systems. If the idea gains traction, it could put pressure on the business models of frontier AI cos. OpenAI and Anthropic.‘ www.ft.com/content/4568... ‘TypeSafe is betting that many routine tasks now handed to expensive general-purpose models can instead be performed by cheaper, more specialised systems. If the idea gains traction, it could put pressure on the business models of frontier AI cos. OpenAI and Anthropic.‘ www.ft.com/content/4568...view source ↗