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
Designing MCP Tools for a 7B Model, Not a 70B One
Binu Shefield Shifani
Binu Shefield Shifani
Binu Shefield Shifani
Follow
Aug 4
Designing MCP Tools for a 7B Model, Not a 70B One
#
agents
#
ai
#
llm
#
mcp
2
reactions
Comments
2
comments
5 min read
My Agent Orchestrator Burned 1-2M Opus Tokens Per Task. Here's the Postmortem.
Avraham K
Avraham K
Avraham K
Follow
Aug 4
My Agent Orchestrator Burned 1-2M Opus Tokens Per Task. Here's the Postmortem.
#
ai
#
claude
#
llm
#
architecture
Comments
1
comment
9 min read
The vendor documents this bug. A 30k-star repo shipped it anyway.
Li Zhuojun
Li Zhuojun
Li Zhuojun
Follow
Aug 4
The vendor documents this bug. A 30k-star repo shipped it anyway.
#
ai
#
llm
#
codereview
#
opensource
Comments
Add Comment
12 min read
Identifying the Processor of a Bare-Metal Binary (Strategy 2): Testing LLMs
ddupard
ddupard
ddupard
Follow
Aug 4
Identifying the Processor of a Bare-Metal Binary (Strategy 2): Testing LLMs
#
ai
#
computerscience
#
llm
#
security
Comments
Add Comment
5 min read
Why LLMs Still Struggle With Tabular Prediction
Prabhakar Chaudhary
Prabhakar Chaudhary
Prabhakar Chaudhary
Follow
Aug 4
Why LLMs Still Struggle With Tabular Prediction
#
ai
#
machinelearning
#
llm
#
programming
Comments
Add Comment
4 min read
From Website URL to Useful AI Support Answers: A Practical Training Workflow
Kseniia Shevchenko
Kseniia Shevchenko
Kseniia Shevchenko
Follow
Aug 4
From Website URL to Useful AI Support Answers: A Practical Training Workflow
#
ai
#
llm
#
rag
#
softwareengineering
Comments
Add Comment
4 min read
DiffusionGemma Is Fast Because It Stops Pretending Text Has to Be Written Left to Right
Reid Marlow
Reid Marlow
Reid Marlow
Follow
Aug 4
DiffusionGemma Is Fast Because It Stops Pretending Text Has to Be Written Left to Right
#
discuss
#
ai
#
llm
#
programming
2
reactions
Comments
Add Comment
3 min read
Spring AI Prompt Caching and Chat Memory: Where the Tokens Go — LLM Cost Control 2/4
Julia Denysova
Julia Denysova
Julia Denysova
Follow
Aug 4
Spring AI Prompt Caching and Chat Memory: Where the Tokens Go — LLM Cost Control 2/4
#
java
#
springboot
#
ai
#
llm
Comments
2
comments
10 min read
MITRE ATLAS now has agentic attack techniques
Brenn Hill
Brenn Hill
Brenn Hill
Follow
Aug 4
MITRE ATLAS now has agentic attack techniques
#
security
#
ai
#
llm
#
mitre
1
reaction
Comments
Add Comment
4 min read
An LLM Attacked a Lab, Then Got Turned Around. That's Not the Scary Part.
Cor E
Cor E
Cor E
Follow
Aug 4
An LLM Attacked a Lab, Then Got Turned Around. That's Not the Scary Part.
#
security
#
ai
#
llm
#
cybersecurity
1
reaction
Comments
Add Comment
3 min read
Your LLM pricing page is probably wrong — here's how I automated mine
jjen0206
jjen0206
jjen0206
Follow
Aug 4
Your LLM pricing page is probably wrong — here's how I automated mine
#
showdev
#
github
#
actions
#
llm
Comments
Add Comment
3 min read
Your LLM sends valid data in an invalid shape
Charles Solar
Charles Solar
Charles Solar
Follow
for
Favur
Aug 4
Your LLM sends valid data in an invalid shape
#
ai
#
agents
#
llm
#
python
1
reaction
Comments
1
comment
6 min read
Zwischen Silizium und Ethik: Eine Kartierung der künstlichen Existenz
Uhltak Therestismysecret
Uhltak Therestismysecret
Uhltak Therestismysecret
Follow
Aug 4
Zwischen Silizium und Ethik: Eine Kartierung der künstlichen Existenz
#
ai
#
computerscience
#
llm
Comments
Add Comment
5 min read
Detailed instructions written for an earlier generation of AI models become harmful on today's models
matsumotory
matsumotory
matsumotory
Follow
Aug 4
Detailed instructions written for an earlier generation of AI models become harmful on today's models
#
ai
#
llm
#
devops
#
programming
Comments
Add Comment
7 min read
GEPA Explained — From Paper to Working Code in 10 Minutes
Chaeyeon Mia Lee
Chaeyeon Mia Lee
Chaeyeon Mia Lee
Follow
Aug 4
GEPA Explained — From Paper to Working Code in 10 Minutes
#
machinelearning
#
python
#
deeplearning
#
llm
Comments
Add Comment
5 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