Login
LLM from scratch, part 28 – training a base model from scratch on an RTX 3090
(gilesthomas.com) by gpjt | view | 121 comments
We gave 5 LLMs $100K to trade stocks for 8 months
(aitradearena.com) by cheeseblubber | view | 307 comments
LLMs are steroids for your Dunning-Kruger
(bytesauna.com) by gridentio | view | 298 comments
Adversarial poetry as a universal single-turn jailbreak mechanism in LLMs
(arxiv.org) by capgre | view | 189 comments
We're losing our voice to LLMs
(tonyalicea.dev) by TonyAlicea10 | view | 402 comments
FAWK: LLMs can write a language interpreter
(martin.janiczek.cz) by todsacerdoti | view | 191 comments
Solving a million-step LLM task with zero errors
(arxiv.org) by Anon84 | view | 95 comments
Show HN: Stun LLMs with thousands of invisible Unicode characters
(gibberifier.com) by wdpatti | view | 111 comments
Ask HN: How are Markov chains so different from tiny LLMs?
by JPLeRouzic | view | 189 comments
Blocking LLM crawlers without JavaScript
(owl.is) by todsacerdoti | view | 101 comments
LLM policy?
(github.com) by dropbox_miner | view | 138 comments
LLMs encode how difficult problems are
(arxiv.org) by stansApprentice | view | 38 comments
Sycophancy is the first LLM "dark pattern"
(seangoedecke.com) by jxmorris12 | view | 104 comments
Show HN: qqqa – A fast, stateless LLM-powered assistant for your shell
(github.com) by iagooar | view | 86 comments
The Bitter Lesson of LLM Extensions
(sawyerhood.com) by sawyerjhood | view | 79 comments
The Learning Loop and LLMs
(martinfowler.com) by johnwheeler | view | 74 comments
Firefox Forcing LLM Features
(equk.co.uk) by birdculture | view | 126 comments
New benchmark shows top LLMs struggle in real mental health care
(swordhealth.com) by RicardoRei | view | 157 comments
LLMs are bullshitters. But that doesn't mean they're not useful
(blog.kagi.com) by speckx | view | 57 comments
New Apple Study Shows LLMs Can Tell What You're Doing from Audio and Motion Data
(9to5mac.com) by andrewrn | view | 33 comments
Agent-o-rama: build, trace, evaluate, and monitor LLM agents in Java or Clojure
(blog.redplanetlabs.com) by yayitswei | view | 5 comments
Anti-patterns while working with LLMs
(instavm.io) by mkagenius | view | 24 comments
Training LLMs for honesty via confessions
(arxiv.org) by arabello | view | 58 comments
Control LLM Spend and Access with any-LLM-gateway
(blog.mozilla.ai) by aittalam | view | 26 comments
Show HN: Anki-LLM – Bulk process and generate Anki flashcards with LLMs
(github.com) by rane | view | 23 comments
Users Stuck in YubiKey Re-Enrollment Loop on X (Twitter)
(twitter.com) by nake13 | view | 71 comments
Llmdeathcount.com
(llmdeathcount.com) by brian_peiris | view | 45 comments
Show HN: An LLM-Powered Tool to Catch PCB Schematic Mistakes
(netlist.io) by wafflesfreak | view | 29 comments
OpenEvolve: Teaching LLMs to Discover Algorithms Through Evolution
(algorithmicsuperintelligence.ai) by codelion | view | 9 comments
Tosijs-schema is a super lightweight schema-first LLM-native JSON schema library
(npmjs.com) by podperson | view | 28 comments
Show HN: Cancer diagnosis makes for an interesting RL environment for LLMs
by dchu17 | view | 20 comments
Show HN: Gerbil – an open source desktop app for running LLMs locally
(github.com) by lone-cloud | view | 12 comments
Teaching an LLM a Niche Diagraming Language
(huy.rocks) by todsacerdoti | view | 3 comments
Apple shows how much faster the M5 runs local LLMs compared to the M4
(9to5mac.com) by geoffbp | view | 2 comments
Show HN: Optimizing LiteLLM with Rust – When Expectations Meet Reality
(github.com) by ticktockten | view | 9 comments
JanitorBench: A new LLM benchmark for multi-turn chats
(about.janitorai.com) by shep101 | view | 6 comments
LLM Output Drift in Financial Workflows: Validation and Mitigation (arXiv)
(arxiv.org) by raffisk | view | 26 comments
Show HN: Gram Functions – Serverless platform for turning code into LLM tools
(speakeasy.com) by disintegrator | view | 0 comments
Show HN: ZigFormer – An LLM implemented in pure Zig
by habedi0 | view | 4 comments
Show HN: Tokenflood – simulate arbitrary loads on instruction-tuned LLMs
(github.com) by twerkmeister | view | 0 comments
Testing LLM Agents Like Software – Behaviour Driven Evals of AI Systems
(aclanthology.org) by PranoyP | view | 11 comments
How to Train an LLM: Part 1
(omkaark.com) by parthsareen | view | 3 comments
Inception releases upgraded Mercury dLLM with improved coding and reasoning
(inceptionlabs.ai) by ddadon10 | view | 3 comments
Show HN: We built an AI tool for working with massive LLM chat log datasets
(hyperparam.app) by platypii | view | 1 comments
Show HN: Extending LLM SVG generation beyond pelicans and bicycles
(gally.net) by tkgally | view | 1 comments
The Stallman Paradox: How Web3 Became the Ultimate Open Source Theater
(paragraph.com) by nabla9 | view | 10 comments
Show HN: CTON: JSON-compatible, token-efficient text format for LLM prompts
(github.com) by daviducolo | view | 1 comments
Meta's Yann LeCun to Launch Physical AI Startup After Declaring LLMs 'Dead End'
(observer.com) by bookofjoe | view | 1 comments
In Support of Richard Stallman
(stallmansupport.org) by ekjhgkejhgk | view | 9 comments
Suppressing ability to lie makes LLM more likely to claim it's conscious
(livescience.com) by thomassmith65 | view | 0 comments