Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
llm
Follow
Hide
Posts
Left menu
👋
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
One TPU Chip, Eight Agents: Serving Small Agent Workloads with Raw JAX
xbill
xbill
xbill
Follow
Jul 29
One TPU Chip, Eight Agents: Serving Small Agent Workloads with Raw JAX
#
tpu
#
llm
#
jax
#
agents
3
reactions
Comments
2
comments
15 min read
Testing Non-Deterministic LLM Pipelines in CI: A Contract-Based Approach
Mukesh
Mukesh
Mukesh
Follow
Jul 30
Testing Non-Deterministic LLM Pipelines in CI: A Contract-Based Approach
#
ai
#
ci
#
llm
#
testing
2
reactions
Comments
1
comment
4 min read
I gave the same fabricated answer to RAGAS and DeepEval. One scored it 0.0. The other scored it 1.0
Nick Lamb
Nick Lamb
Nick Lamb
Follow
Jul 30
I gave the same fabricated answer to RAGAS and DeepEval. One scored it 0.0. The other scored it 1.0
#
ai
#
llm
#
rag
#
testing
Comments
Add Comment
6 min read
Your cache_read_input_tokens is zero. Here is what silently did it.
Jackson Ly
Jackson Ly
Jackson Ly
Follow
Jul 30
Your cache_read_input_tokens is zero. Here is what silently did it.
#
llm
#
ai
#
performance
#
api
Comments
Add Comment
5 min read
Close your editor before heavy jobs? The heavy job lives inside my editor
Jun
Jun
Jun
Follow
Jul 30
Close your editor before heavy jobs? The heavy job lives inside my editor
#
llm
#
memory
#
applesilicon
#
debugging
Comments
Add Comment
4 min read
Four Models Cited My Numbers Perfectly. One Still Misread Them.
John
John
John
Follow
Jul 30
Four Models Cited My Numbers Perfectly. One Still Misread Them.
#
ai
#
analytics
#
data
#
llm
Comments
Add Comment
6 min read
OpenEval: Why LLM Evaluation Needs a Standard Format
Adha AK
Adha AK
Adha AK
Follow
Jul 30
OpenEval: Why LLM Evaluation Needs a Standard Format
#
llm
#
evaluation
#
ai
#
testing
Comments
Add Comment
1 min read
Your AI Subagents Are Lying to You: 4 Silent Failure Modes
Wessam Ibrahim
Wessam Ibrahim
Wessam Ibrahim
Follow
Jul 29
Your AI Subagents Are Lying to You: 4 Silent Failure Modes
#
claudecode
#
ai
#
llm
#
agents
1
reaction
Comments
3
comments
4 min read
Why does parsing scientific papers for RAG still break on equations and tables?
Santiago Garcia
Santiago Garcia
Santiago Garcia
Follow
Jul 29
Why does parsing scientific papers for RAG still break on equations and tables?
#
ai
#
llm
#
rag
2
reactions
Comments
Add Comment
3 min read
Building a unified OpenAI-compatible gateway for 16 Chinese LLMs: architecture notes on routing, payments and ops
Martin-hhht
Martin-hhht
Martin-hhht
Follow
Jul 30
Building a unified OpenAI-compatible gateway for 16 Chinese LLMs: architecture notes on routing, payments and ops
#
ai
#
api
#
architecture
#
llm
Comments
1
comment
3 min read
`finish_reason=length` Returned Empty Content — and the Error Message Lied to Me
Milo Bergstrom
Milo Bergstrom
Milo Bergstrom
Follow
Jul 30
`finish_reason=length` Returned Empty Content — and the Error Message Lied to Me
#
llm
#
debugging
#
typescript
#
ai
1
reaction
Comments
Add Comment
3 min read
Model + Harness = Agent: The Gap Isn’t Where You Think
OctoLab
OctoLab
OctoLab
Follow
Jul 29
Model + Harness = Agent: The Gap Isn’t Where You Think
#
ai
#
agents
#
llm
#
programming
Comments
Add Comment
4 min read
I Trust My AI Completely—Except When It Says “Done”
OctoLab
OctoLab
OctoLab
Follow
Jul 29
I Trust My AI Completely—Except When It Says “Done”
#
ai
#
agents
#
llm
#
programming
1
reaction
Comments
1
comment
4 min read
How to Build an AI Kill Switch (and Why Every Agent Needs One)
Brenn Hill
Brenn Hill
Brenn Hill
Follow
Jul 29
How to Build an AI Kill Switch (and Why Every Agent Needs One)
#
ai
#
machinelearning
#
llm
#
programming
1
reaction
Comments
Add Comment
9 min read
From RAG to Agentic AI. How I Added LangGraph to My Local
TAGBA G-Josaphat E.
TAGBA G-Josaphat E.
TAGBA G-Josaphat E.
Follow
Jul 29
From RAG to Agentic AI. How I Added LangGraph to My Local
#
rag
#
langraph
#
agents
#
llm
1
reaction
Comments
1
comment
6 min read
👋
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account