公式動画ピックアップ
AAPL
ADBE
ADSK
AIG
AMGN
AMZN
BABA
BAC
BL
BOX
C
CHGG
CLDR
COKE
COUP
CRM
CROX
DDOG
DELL
DIS
DOCU
DOMO
ESTC
F
FIVN
GILD
GRUB
GS
GSK
H
HD
HON
HPE
HSBC
IBM
INST
INTC
INTU
IRBT
JCOM
JNJ
JPM
LLY
LMT
M
MA
MCD
MDB
MGM
MMM
MSFT
MSI
NCR
NEM
NEWR
NFLX
NKE
NOW
NTNX
NVDA
NYT
OKTA
ORCL
PD
PG
PLAN
PS
RHT
RNG
SAP
SBUX
SHOP
SMAR
SPLK
SQ
TDOC
TEAM
TSLA
TWOU
TWTR
TXN
UA
UAL
UL
UTX
V
VEEV
VZ
WDAY
WFC
WK
WMT
WORK
YELP
ZEN
ZM
ZS
ZUO
公式動画&関連する動画 [Pop Goes the Stack | The Impact of Inference: Reliability | AI]
Traditional reliability meant consistency. Given identical inputs, systems produced identical outputs. Costs were stable and behavior predictable. Inference reliability on the other hand is shaped by nondeterminism. Outputs vary due to stochastic generation, retraining introduces drift, and token-based billing can cause cost fluctuations. The new dimension of reliability is semantic consistency, that is, the ability to deliver outputs of acceptable quality, accuracy, and predictability over time despite probabilistic behavior.
In this episode of Pop Goes the Stack, #F5's Lori MacVittie and Joel Moses are joined by guests Ken Arora and Kunal Anand as they dive into the topic of reliability in #AI systems. They explore the concept of 'slop' (AI variability) as a potential feature rather than a bug, discuss the importance of contextual semantic consistency, and weigh guardrails and evals tailored to specific inference workloads. Tune in to learn how to navigate the evolving AI landscape and take note of practical tools and strategies like multi-model chaining, distillation, and prompt engineering to ensure reliability.
Chapters:
00:00 Welcome to Pop Goes the Stack
00:47 Inference: Why reliability isn't what it used to be
02:00 The case for AI 'creativity' (Slop or Jazz?)
05:55 Context is key for reliability
06:45 Semantic consistency in agentic AI
07:55 The role of guardrails and context
09:16 Evals are critical to agentic composition
12:31 Defining and measuring semantic consistency
15:48 Is AI reliability subjective?
16:46 Multi-model chains and AI refinement
17:49 Staging vs. production in AI systems
19:00 Key takeaways: Know your problem, guardrails and evals, & pragmatism
Find out more in the blog How AI inference changes application delivery: https://go.f5.net/cxd0imiv
Learn how you can stay ahead of the curve and keep your stack whole with additional insights on #AppSecurity, multicloud, AI, and emerging tech: https://go.f5.net/h33oydn2
More about F5: https://go.f5.net/s12cpz9q
Read our blog: https://go.f5.net/3dy52zk3
Follow us on LinkedIn: https://go.f5.net/s2arxbc3
169
4