Mikyo
@mikeldking.bsky.social did:plc:nvwnb6g7kxgjnitgw2pqjyyi
Building the future of OSS AI observability ☕️🚲🧗🏻♂️🏂⛰🕴
Bluesky’a katılma tarihi:
- Takipçi
- 54
- Takip edilen
- 29
- Post
- 128
- Sıralamaya girdiği gün
- 0
Özet
Mikyo (@mikeldking.bsky.social), 12 Temmuz 2023 tarihinde katılan bir Bluesky kullanıcısı. 54 takipçisi var, 29 hesabı takip ediyor ve 128 post paylaştı.
Sıralama geçmişi
Bu hesabın postlarının Debya günlük listesine girdiği en iyi günler.
Bu hesap henüz günlük sıralamaya girmedi.
Son beğendiği postlar
Bluesky ağındaki herkese açık beğeniler.
One code-mode test I’d run: start a long query, interrupt after execution begins, then retry the same intent. PASS = cancellation and retry are separate traces, no duplicate side effects, and the agent can distinguish transport vs tool vs code errors.
Postu gösterAs agents gain capabilities due to skills, MCPs, and codemode, evaluating agents becomes increasingly more difficult because you need to test across multiple environments and harnesses. Arize Phoenix your benchmarking Harbor runs so pinpointing improvements and regressions becomes tractable.
Postu gösterWe put PXI, Claude Code, and Codex through the same tasks with Harbor + Phoenix Even when agents succeeded, their traces told different stories: tool calls, latency, and efficiency. Join Oct 8 at 11am PT / 2pm ET to learn how to compare agents and inspect ATIF traces. luma.com/arizeai-ben...
Postu gösterWe’re going live in 30 minutes for our webinar on Benchmarking AI Agents & Tool Use with Harbor and Arize Phoenix! Join here: luma.com/arizeai-ben...
Postu gösternew baselining capabilities for experiments Now when you have a baseline set on your experiments or when you care comparing two experiments, you can see the deltas of your evals, tokens, latency and cost so you can quickly identify regressions and improvements.
Postu göster
Blokladığı hesaplar
Bluesky’da bloklar herkese açık kayıtlardır.
Bu hesap kimseyi bloklamıyor.