Hackernews posts about Tolkien

Tolkien is a renowned English author, philologist, and professor best known for creating the fictional Middle-earth world and characters in his fantasy stories.

1. My security camera shipped a GitHub admin token in its login page (hhh.hn)
   645 points by hhh 25 days ago | 243 comments
2. GigaToken: ~1000x faster Language model tokenization (github.com)
   620 points by syrusakbary 27 days ago | 120 comments
3. The relay market powering token resellers and fraud (vectoral.com)
   209 points by mlenhard 23 days ago | 136 comments
4. Zero-Mem: Zero-Token Memory Operations for LLM Agents (arxiv.org)
   101 points by theanonymousone 14 days ago | 12 comments
5. TokenTown: A visual way to understand how LLMs work (laurentiugabriel.github.io)
   74 points by laurentiurad 20 days ago | 21 comments
6. Show HN: Mcptoon – Token-efficient MCP CLI client (github.com)
   73 points by mcptokensaver 7 days ago | 49 comments
7. Launch HN: Tokenless (YC S26) – Automatic model switching to save money (usetokenless.com)
   71 points by rohaga 20 days ago | 63 comments
8. Brazilian farmers tokenized dairy cows to get loans, bypassing bank limits (www.coindesk.com)
   61 points by paulpauper 24 days ago | 54 comments
9. AI Mania: From Tulips to Tokens (seanhelvey.com)
   49 points by Lambda11 16 days ago | 56 comments
10. Does Speaking to Agents Like Cavemen Save 65% of Tokens? We Test (blog.jetbrains.com)
    46 points by Sandman 21 days ago | 41 comments
11. Is the industry ready for tokens-constrained work? (blog.alaindichiappari.dev)
    41 points by fullautomation 2 days ago | 71 comments
12. Show HN: Graft – Claude Code hooks that cut grep tokens by 42% (github.com)
    39 points by shrishdwi 4 days ago | 44 comments
13. Claude Code pricing: same tokens, same model, up to 40x the price (quesma.com)
    31 points by jakozaur 7 days ago | 10 comments
14. Gigatoken: Fastest Tokenizer (twitter.com)
    26 points by convexstrictly 28 days ago | 5 comments
15. Unlimited AI tokens aren't unlimited after all as US Army burns through supply (arstechnica.com)
    25 points by Bender 27 days ago | 7 comments
16. The Tokenpocalypse Is Here: Companies Are Scrambling to Stop Spending on AI (www.404media.co)
    22 points by swolpers 11 days ago | 6 comments
17. How do programming languages impact token efficiency and correctness? (danluu.com)
    18 points by matt_d 9 days ago | 1 comments
18. I sent Claude Opus 5 '–-' and it wrote me 5k tokens about a cartographer (austinsnerdythings.com)
    16 points by auspiv 21 days ago | 6 comments
19. Gumroad Says That It's Now Spending as Much on Human Employees as AI Tokens (officechai.com)
    14 points by nigelgutzmann 28 days ago | 13 comments
20. Show HN: Tura – Build agent that uses 80% less token and delivers better results (github.com)
    14 points by turaainet 10 days ago | discuss
21. AI Tokenomics: What AI tokens cost and where they're wasted (github.com)
    13 points by bkotrys 23 days ago | discuss
22. Microsoft Tells Engineers 'Tokenmaxxing Is Not What We Are Optimizing For' (www.404media.co)
    11 points by Brajeshwar 13 days ago | 4 comments
23. Celeris-1: A diffusion LLM benchmarked at 2,082 output tokens/s (artificialanalysis.ai)
    11 points by jn2clark 13 days ago | 1 comments
24. Microsoft Tells Engineers 'Tokenmaxxing Is Not What We Are Optimizing For (www.404media.co)
    11 points by cdrnsf 14 days ago | discuss
25. TokenTown –> Learn how LLM's work in a SimCity-like world (laurentiugabriel.github.io)
    10 points by laurentiurad 22 days ago | 4 comments
26. Show HN: Awsmux – Multi-account AWS CLI, up to 5.4x faster, 7.4x fewer tokens (github.com)
    10 points by 0hardik1 24 days ago | 4 comments
27. Memelang: Token-Terse Query Language (memelang.net)
    10 points by bri-holt 12 days ago | 3 comments
28. Headroom - compress AI agent input for reduced token usage w/out harming output (github.com)
    10 points by andsoitis 28 days ago | 2 comments
29. Nvidia Vera Rubin Driving Performance per Watt, Lowest Token Cost for Partners (www.hpcwire.com)
    10 points by rbanffy 28 days ago | 2 comments
30. AI 'tokenmaxxing' fades as workplaces look to cut tech spending (apnews.com)
    10 points by geox 21 days ago | 1 comments