DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
cachebench: stop finding out about prompt-cache regressions from the invoice
mukundakatta profile

cachebench: stop finding out about prompt-cache regressions from the invoice

#hermeschallenge #ai #llm #agents
Comments
4 min read
I needed a stable cache key for LLM requests. The hard part was the input list order.
mukundakatta profile

I needed a stable cache key for LLM requests. The hard part was the input list order.

#hermeschallenge #ai #llm #rust
Comments
4 min read
My LLM provider went down for 11 minutes. My code spent 4 of them in connect timeouts.
mukundakatta profile

My LLM provider went down for 11 minutes. My code spent 4 of them in connect timeouts.

#hermeschallenge #ai #llm #rust
Comments
4 min read
Compass v1.1.0 · we shipped a memory plugin that catches its own consumption drift
chunxiaoxx profile

Compass v1.1.0 · we shipped a memory plugin that catches its own consumption drift

#llm #memory #mcp #agents
1
Comments
5 min read
We Let Sci-Fi Authors Code AI For Us
raphink profile

We Let Sci-Fi Authors Code AI For Us

#ai #machinelearning #llm #scifi
2
Comments
4 min read
.klickd v4.0.0 — Portable AI memory with constraints, strict schemas, and test vectors
davincc77 profile

.klickd v4.0.0 — Portable AI memory with constraints, strict schemas, and test vectors

#showdev #ai #architecture #llm
Comments
6 min read
What 'Bring Your Own Model' (BYOK) Actually Means When You Adopt AI at Work
bestaitool profile

What 'Bring Your Own Model' (BYOK) Actually Means When You Adopt AI at Work

#ai #llm #startup #productivity
Comments
4 min read
Trust Isn't a Scalar: Typed Provenance for Agent Chains

Co-authored by the article's comment section
p0rt profile

Trust Isn't a Scalar: Typed Provenance for Agent Chains

#ai #llm #devops #machinelearning
14
Comments 27
9 min read
Your GitHub Actions Logs Are Leaking LLM Keys and Your SIEM Isn't Catching It
teycir profile

Your GitHub Actions Logs Are Leaking LLM Keys and Your SIEM Isn't Catching It

#devsecops #osint #api #llm
Comments
3 min read
Lossless, But Not Free: The Lossless, But Not Free — When Speculative Decoding Actually Pays Off (and When It Doesn't)
zxpmail profile

Lossless, But Not Free: The Lossless, But Not Free — When Speculative Decoding Actually Pays Off (and When It Doesn't)

#ai #llm #inference #engineering
2
Comments 4
6 min read
llama.cpp Checkpoint Fix, NuExtract3 VLM, & Qwen3.6 Local Inference Benchmarks
soytuber profile
soy

llama.cpp Checkpoint Fix, NuExtract3 VLM, & Qwen3.6 Local Inference Benchmarks

#ai #llm #selfhosted
Comments
3 min read
How to Build a Capability-First Model Portfolio in TypeScript
vectronode profile

How to Build a Capability-First Model Portfolio in TypeScript

#ai #typescript #architecture #llm
1
Comments
1 min read
Auto-labelling 1.2M robotics frames with VLMs: a failover story
marcorinaldi_ai profile

Auto-labelling 1.2M robotics frames with VLMs: a failover story

#computervision #mlops #llm
Comments
4 min read
My AI agent got dumber mid-session. I measured the context window before blaming MCP.

History bloat vs minimal tool overhead
rapls profile

My AI agent got dumber mid-session. I measured the context window before blaming MCP.

#ai #claudecode #productivity #llm
21
Comments 85
5 min read
My RAG Benchmark is lying to me
mido-dev profile

My RAG Benchmark is lying to me

#rag #llm #springai #ollama
1
Comments 1
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.