21. we're seeing our coding agent costs decrease significantly for second month in row longer blog on t... we're seeing our coding agent costs decrease significantly for second month in row longer blog on this later, but three quick steps we took 1/ cost visibility. you cant control 10/04 18:39 ♡
22. specialized agents or one mega agent? we're having this debate internally... specialized agents or one mega agent? we're having this debate internally... a16z @a16z . @OpenRouter co-founder Alex Atallah on personal agents: 10 specialized chiefs of staff 10/04 04:05 ♡
23. cool project by @dbreunig in langchain this is ModelRouterMiddleware - jev reads the first message,... cool project by @dbreunig in langchain this is ModelRouterMiddleware - jev reads the first message, picks the model, and that model handles the whole run jev is cheap enough that y 10/04 04:05 ♡
24. good pattern from this google paper the verifier starts from a clean context, so the explorer's rea... good pattern from this google paper the verifier starts from a clean context, so the explorer's reasoning can't talk it into a bad proof so the explorer can try wild ideas 10/03 01:42 ♡
25. every agent team ends up wanting its own review ui over their traces - LangSmith Custom Apps lets yo... every agent team ends up wanting its own review ui over their traces - LangSmith Custom Apps lets you build it on your own data and ship it right into the workspace x.com/LangChain 10/03 01:33 ♡
26. Memory is hard to get working well, especially in a company setting Making some improvements to how... Memory is hard to get working well, especially in a company setting Making some improvements to how we memory in managed deepagents! Caspar @caspar_br User memory in Managed Deep A 10/03 00:13 ♡
27. congrats @AravSrinivas! more entrants in the decision model class, and this one is open weights che... congrats @AravSrinivas ! more entrants in the decision model class, and this one is open weights cheap typed answers for the small calls inside a harness (routing, approvals, judgi 10/02 07:45 ♡
28. pretty clear every agent harness needs a durable runtime pi :: pi-durable deepagents :: langgraph pretty clear every agent harness needs a durable runtime pi :: pi-durable deepagents :: langgraph Pi @pidotdev People of Pi: We've shipped Pi 1.0 with Pi Durable. Go make them 10/02 06:45 ♡
29. decision model season indeed said there'd be more entrants before long - now open weights too, nice... decision model season indeed said there'd be more entrants before long - now open weights too, nice work @ritakozlov + the cloudflare team your harness should be able to swap i 10/02 01:37 ♡
30. model routing - "no one knows what it means, but its provocative, gets the people going" we try to ... model routing - "no one knows what it means, but its provocative, gets the people going" we try to shed light on how to do it properly 1. understand tasks 2. understand the models 10/02 01:24 ♡
