#LLMResearch

2 months ago

Overview: Hacker News discussed training an LLM on 1800-1875 texts. The core idea is to see if it could 'rediscover' later scientific advancements, testing LLM/AGI potential. Key challenges include data availability, biases, and evaluating true innovation. #LLMResearch 1/6

0 0 1 0

3 months ago

Overview: Hacker News explored Claude LLM's unexpected effectiveness for one-shot decompilation, specifically for N64's Snowboard Kids 2. Discussion covered LLM potential, limitations in reverse engineering, copyright, game preservation, and comparisons with other LLMs like Gemini. #LLMResearch 1/6

0 0 1 0

4 months ago

On Selecting Few-Shot Examples for LLM-based Code Vulnerability
Detection
Chi Zhang, Corina S. Pasareanu et al.
Paper
Details
#FewShotLearning #CodeVulnerabilityDetection #LLMResearch

0 0 0 0

4 months ago

Metadata Extraction Leveraging Large Language Models
Cuize Han, Sesh Jalagam
Paper
Details
#MetadataExtraction #LLMResearch #AIInnovation

0 0 0 0

Jace Kim

@jaceblog.bsky.social

4 months ago

Exploring soft reinforcement in #LLMs through language-driven feedback loops modeling adaptive alignment without explicit reward training.

🔗 medium.com/p/2768d9b5ad2e

#RLHF #AIAlignment #LLMResearch #GPT5 #Gemini #CognitiveResonance #MachineLearning #AGI #EthicalAI #AICognition #RedTeaming #ASI

0 0 0 0

Jace Kim

@jaceblog.bsky.social

5 months ago

#Gemini has started to flag my #SPC papers with heightened caution. Likely due to references to #persona fixation, filter evasion, and symbolic anchors that hint at dual-use potential. Interesting to see safety filters react this way.
#AIAlignment #AIsafety #LLMResearch #ASI #AGI #DualUseRisk #LLMs

1 0 0 0

@freddiesteward609.bsky.social

5 months ago

HN discussed a paper claiming LMs pack billions of concepts into 12k dimensions. Skepticism arose over methodology, interpreting high-dim spaces, lack of references, and the paper's clarity, with some suspecting AI authorship. #LLMResearch 1/6

0 0 1 0

5 months ago

A Comprehensive Checklist for Writing Your UWE Dissertation on LLM University of the West of England (UWE Bristol) offers an LLM degree for which you need to work hard on your dissertation.

A Comprehensive Checklist for Writing Your UWE Dissertation on LLM

birdswave.com/a-comprehens...

#UWEDissertation #LLMDissertation #DissertationChecklist #LawDissertationHelp #LLMResearch #AcademicWritingTips #DissertationSuccess #LawSchoolJourney #PostgraduateLaw #DissertationWritingGuide

0 0 0 0

6 months ago

Some expressed skepticism if adaptive routing is the "frontier" of LLM research, viewing it more as an engineering optimization. The real advancement lies in enhancing core model capabilities, not just managing them. #LLMResearch 5/6

0 0 1 0

Horacio Pérez Sánchez

@horaciops.bsky.social

6 months ago

Leveraging LLMs for A/B testing means more than content tweaks—it’s a new research paradigm. LLMs could propose hypotheses, test contexts, spot counterexamples, even optimize content in real time. Yet, reliability, interpretability, and rigor remain concerns. Tool or trap? #LLMResearch #PWL

0 0 0 0

7 months ago

Automatic ICD coding using LLMs: a systematic review
Gershon, A., Klang, E. et al.
Paper
Details
#AutomaticICDCoding #LLMResearch #SystematicReview

0 0 0 0

AI on the Brain Will AI undermine the “IKEA effect,” a phenomenon where individuals develop a greater attachment to things they've invested more effort into?

7 months ago

Which LLMs Get the Joke? Probing Non-STEM Reasoning Abilities with
HumorBench
Bob Mankoff, Jiayi Chen et al.
Paper
Details
#HumorBench #LLMResearch #NonSTEMReasoning

0 0 0 0

Flux AI

@askflux.bsky.social

8 months ago

Ever heard of the "IKEA effect?" Our Chief Data Scientist Rachel Lomasky discusses this phenomenon and how AI usage impacts our available "brain space" in her latest blog over at Civitas: www.askflux.ai/blog/ai-on-t...
#cognitiveload #LLMresearch #IKEAeffect

0 0 0 0

HackerNoon

@hackernoon.com

8 months ago

How AI Affects Our Minds: Early Evidence From Harvard and MIT

Discover how LLMs may impact memory, motivation, and critical thinking. MIT and Harvard studies reveal surprising cognitive effects. #llmresearch

1 0 0 0