Llms - DEV Community

Skip to content

DEV Community

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

Ali Ahmed

Nov 5

How to stop an LLM from inventing numbers: evidence containment and numeral tracing

#aiengineering #llms #hallucinations #evaluation

3 min read

Ali Ahmed

Nov 5

How I got my first pull request merged into LiteLLM

#opensource #aiengineering #llms

2 min read

Ali Ahmed

Nov 5

Streaming LLM output through a Next.js proxy: why you only get stream_end

#nextjs #streaming #llms #webdev

3 min read

Ali Ahmed

Nov 5

Why LLM cost dashboards lie when two deployments share a model name

#aiengineering #llms #opensource #finops

3 min read

RC

Nov 5

Trust does not carry forward

#llms #hallucination #modelevaluation

3 min read

Daniel Sam Pete Thiyagu

Nov 4

109 Million Beats 72 Billion: LeCun's Theorem Says Every Model Sees the Same World

#ai #machinelearning #llms #technews

8 min read

Daniel Sam Pete Thiyagu

Nov 3

10 Hours to 3: How KAIST's CluSTER Picks the 31% of Data That Actually Teaches

#ai #machinelearning #technews #llms

6 min read

Nov 2

The Gaps in the Map Are Not Ideas

#ai #embeddings #llms #research

13 min read

Daniel Sam Pete Thiyagu

Nov 1

Stop Typing One Token at a Time: The Coarse-to-Fine Model That's 31 Faster

#ai #machinelearning #llms #technews

6 min read

Daniel Sam Pete Thiyagu

Oct 30

The Mean Lied: How a Second Statistic Fixed Long-Context Memory

#ai #machinelearning #llms #technews

6 min read

Natalia Cherkasova

Oct 29

Evaluating Academic Review Methods: Comparing LLMs and Human Reviewers for Error Detection and Integrity

#llms #academicreview #ai #ethics

10 min read

RC

Oct 28

Claude rediscovered CVE-2026-56132 proving 123 libraries crash-free

#formalverification #llms #softwaresecurity

4 min read

Daniel Sam Pete Thiyagu

Oct 27

90.5% to 81.0%: The Open Model That Ships Weaker on Purpose

#ai #llms #machinelearning #technews

6 min read

Daniel Sam Pete Thiyagu

Oct 26

43% Fewer Tokens, 98.9% of the Quality: How VisionWeave Spends Visual Tokens Like Money

#ai #machinelearning #llms #technews

6 min read

Daniel Sam Pete Thiyagu

Oct 24

The Lookup Table That Beat 17 Experts: DeepSeek's Engram and the Second Axis of Sparsity

#ai #machinelearning #llms #technews

5 min read

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