post training infra

Feeds to Scour
SubscribedAll
Scoured 254 posts in 13.8 ms

Reasoning RL in 2026: GRPO, DPO, RLVR, Agentic PO & Beyond

 🎯RLHF
turingpost.com·

Which LoRA? An Empirical Study on the Effectiveness of LoRA Techniques During Multilingual Instruction Tuning

 🎛️Fine-Tuning  Content type: Academic
arxiv.org·

Fine-tuning Large Language Models (LLMs) using PEFT

 🎛️Fine-Tuning  Content type: Blog
medium.com
·

Tracing Eval-Awareness Emergence Through Training of OLMo 3

 🎯RLHF
lesswrong.com·

brunokeymolen/lora: LoRa (Long Range) communication related projects

 🎛️Fine-Tuning  Content type: Code
github.com··Hacker News

Meshcore and Haiku: a Match Apparently Made in Italy

 🎛️Fine-Tuning
hackaday.com·

SecLoRA: Secure Aggregation of Low-Rank Matrix Products via Functional Encryption

 🎛️Fine-Tuning
eprint.iacr.org·

Fine-tune FLUX.2 [Klein] with a LoRA under 60 minutes

 🎛️Fine-Tuning  Content type: Blog
Less-relevant results

The week AI infrastructure crossed from a technology story to a financial one

 🎯RLHF  Content type: News
mlwhiz.com·

New comment by bkjlblh in "Claude Fable 5"

 🎛️Fine-Tuning  Content type: Discussion

Anthropic Apologizes For One of the Guardrails on Its Fable 5 Model, and Will Change It

 🎛️Fine-Tuning
gizmodo.com·

Robust Multi-Mutant Protein Stability Prediction from a Fine-Tuned Evolutionary Scale Model

 🎛️Fine-Tuning  Content type: Academic
biorxiv.org·

Replicate vs Gemini API: An Honest Cost Breakdown of Photo Generation (Real Production Numbers)

 🎛️Fine-Tuning  Content type: Blog
medium.com·

fc2

 🎛️Fine-Tuning
yog.ink·

Anthropic's Fable 5 Silent Sabotage Mode

 🎛️Fine-Tuning
everettdutton.com··Hacker News

If Claude Fable stops helping you, you’ll never know

 🎛️Fine-Tuning

Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training

 🎛️Fine-Tuning  Content type: Academic
arxiv.org·

Introducing the Google Colab CLI

 🎛️Fine-Tuning  Content type: Blog

Anthropic releases Claude Fable 5 and Mythos 5 with major gains in coding and science

 🎛️Fine-Tuning
oodaloop.com·

Why LLMs (still) lack taste

 🎯RLHF

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help