DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Stop Fine-Tuning Your Model. Your Architecture Is the Problem.

Stop Fine-Tuning Your Model. Your Architecture Is the Problem.

Comments
4 min read
Rebuilding the Cerebras Knowledge Base: an LLM reranker

Rebuilding the Cerebras Knowledge Base: an LLM reranker

Comments
5 min read
Rebuilding the Cerebras Knowledge Base: LLM distillation and bursting

Rebuilding the Cerebras Knowledge Base: LLM distillation and bursting

Comments
5 min read
Your text-to-SQL eval is lying: the gateway returns HTTP 200 with the error in the body

Your text-to-SQL eval is lying: the gateway returns HTTP 200 with the error in the body

Comments 1
3 min read
Part 3: Build the Eval Set Before the Agent Exists

Part 3: Build the Eval Set Before the Agent Exists

Comments
4 min read
Meta āđ€āļ›āļīāļ”āļ•āļąāļ§ Muse Glimmer 30B, āđ‚āļĄāđ€āļ”āļĨ Open-Weight āļ—āļĩāđˆāļĢāļąāļ™āļšāļ™āđ‚āļ™āđ‰āļ•āļšāļļāđŠāļāđ„āļ”āđ‰ āđāļĨāļ°āđ€āļ”āļīāļĄāļžāļąāļ™āļ„āļĢāļąāđ‰āļ‡āđƒāļŦāļāđˆāļ‚āļ­āļ‡ Zuckerberg

Meta āđ€āļ›āļīāļ”āļ•āļąāļ§ Muse Glimmer 30B, āđ‚āļĄāđ€āļ”āļĨ Open-Weight āļ—āļĩāđˆāļĢāļąāļ™āļšāļ™āđ‚āļ™āđ‰āļ•āļšāļļāđŠāļāđ„āļ”āđ‰ āđāļĨāļ°āđ€āļ”āļīāļĄāļžāļąāļ™āļ„āļĢāļąāđ‰āļ‡āđƒāļŦāļāđˆāļ‚āļ­āļ‡ Zuckerberg

Comments
3 min read
BitNet, Microsoft āđ€āļ›āļīāļ”āļ‹āļ­āļĢāđŒāļŠāđ€āļŸāļĢāļĄāđ€āļ§āļīāļĢāđŒāļāļ—āļĩāđˆāļĢāļąāļ™ LLM 100B āļžāļēāļĢāļēāļĄāļīāđ€āļ•āļ­āļĢāđŒāļšāļ™ CPU āļ•āļąāļ§āđ€āļ”āļĩāļĒāļ§

BitNet, Microsoft āđ€āļ›āļīāļ”āļ‹āļ­āļĢāđŒāļŠāđ€āļŸāļĢāļĄāđ€āļ§āļīāļĢāđŒāļāļ—āļĩāđˆāļĢāļąāļ™ LLM 100B āļžāļēāļĢāļēāļĄāļīāđ€āļ•āļ­āļĢāđŒāļšāļ™ CPU āļ•āļąāļ§āđ€āļ”āļĩāļĒāļ§

Comments
2 min read
Supplier Invoice Extraction: Prompt Routing, Small-Model-First Fallback, and Batch Runs

Supplier Invoice Extraction: Prompt Routing, Small-Model-First Fallback, and Batch Runs

Comments 1
6 min read
Building a Deal Intelligence Agent with Persistent Multi-Deal Memory

Building a Deal Intelligence Agent with Persistent Multi-Deal Memory

1
Comments
4 min read
The Small Language Model Revolution: Why Fit Beats Force

The Small Language Model Revolution: Why Fit Beats Force

Comments
8 min read
I Benchmarked Two Local LLMs on Real Dev Work — Qwopus 27B vs Muse Glimmer 30B

I Benchmarked Two Local LLMs on Real Dev Work — Qwopus 27B vs Muse Glimmer 30B

Comments
5 min read
Selection pressure turns benchmarks into fingerprints

Selection pressure turns benchmarks into fingerprints

Comments
4 min read
Quantization Shrinks Large AI Models Without Breaking Them

Quantization Shrinks Large AI Models Without Breaking Them

Comments
1 min read
Part 2: Pinning the Use Case and Writing Tool Contracts Like Specs

Part 2: Pinning the Use Case and Writing Tool Contracts Like Specs

Comments
4 min read
I scanned my own 30 days of Claude Code logs. Here's what I found (and the tool I built to do it)

I scanned my own 30 days of Claude Code logs. Here's what I found (and the tool I built to do it)

Comments
3 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.