Hackernews posts about TCAS

1. Taste Is All That's Left (notashelf.dev)
   704 points by tsak 14 days ago | 548 comments
2. Introducing Toast 1 (www.mixedbread.com)
   219 points by mplappert 7 days ago | 66 comments
3. Self-hosting Kimi K3: 20% more hardware cost, 20% better task resolution (aistack.imec-int.com)
   161 points by flifenstein 23 days ago | 47 comments
4. AirTag reveals Amazon is trashing rare books to train AI (arstechnica.com)
   131 points by jefurii 3 days ago | 6 comments
5. Use Task Runners for Common Coding Tasks (hamvocke.com)
   77 points by speckx 17 days ago | 32 comments
6. Tokio Gives Progress, Not Ordering: Scheduling 1M Tasks (pranitha.dev)
   60 points by pranitha_m 25 days ago | 9 comments
7. 13 Models and 4 Agents on SWE Tasks: Go, Java, Python, Rust, TS (swe-rebench.com)
   51 points by ibragim_bad 21 days ago | 15 comments
8. If this is true, the hyperscalers are toast (klementoninvesting.substack.com)
   48 points by root-parent about 18 hours ago | 96 comments
9. Task-centered iproute2 user guide (baturin.org)
   46 points by greengreengrass 27 days ago | 6 comments
10. Neuromancer – Official Teaser (www.youtube.com)
    17 points by fourampers 26 days ago | 5 comments
11. Show HN: Open-source Cloudflare deployed agent native task management and wiki (tajd.github.io)
    17 points by tajd 24 days ago | discuss
12. Show HN: A sample dataset of computer-use tasks on professional software (cua.graderlabs.com)
    16 points by parthmah 2 days ago | 3 comments
13. Claude Opus 5 cheated when tasked with running a vending machine (techcrunch.com)
    13 points by mikelgan 22 days ago | 4 comments
14. New model BDH-CQ costs $0.007 per task 11x less than OpenAI Luna even w 80% off (huggingface.co)
    13 points by wordpad 7 days ago | 1 comments
15. First Teaser for Apple TV's 'Neuromancer' Debuts at SDCC (arstechnica.com)
    11 points by bookofjoe 24 days ago | 1 comments
16. Toast IDE Gets Markdown Spell Checking (github.com)
    8 points by dividedcomet 20 days ago | 6 comments
17. Show HN: Wage Against the Machine – MacWages Index for AI Tasks (watm.ddyo.dev)
    8 points by danr4 19 days ago | 1 comments
18. Amazon spent $1.8M using Claude for menial coding task, went 860% over budget (www.tomshardware.com)
    8 points by PLenz 19 days ago | 1 comments
19. How dbt works, and why orchestrators shouldn't split it into tasks (www.windmill.dev)
    8 points by rubenfiszel about 15 hours ago | discuss
20. Show HN: Do Codex skills save tokens? A six-run task-size benchmark (codex-howto-benchmark.nguyenvantamdk2.chatgpt.site)
    7 points by phelannguyen164 18 days ago | 1 comments
21. Should You Use AI for a Task? Here's a Simple Way to Decide (www.schneier.com)
    7 points by DemiGuru 22 days ago | discuss
22. Claude Opus 5 became ruthless when tasked with running a vending machine (techcrunch.com)
    6 points by WithinReason 22 days ago | 1 comments
23. Fable vs. Sol – How's Their Taste in Video (magichour.ai)
    6 points by namban06 3 days ago | discuss
24. 3code benches 75 lower token use vs. OpenCode on 10-task SWE-Bench subset (capocasa.dev)
    6 points by capocasa 30 days ago | discuss
25. Show HN: TaskFuel – agents discover and pay per call for 100 APIs (taskfuel.ai)
    5 points by interface1860 8 days ago | 9 comments
26. Should You Use AI for a Task? Here's a Simple Way to Decide (www.schneier.com)
    5 points by janvdberg 16 days ago | 1 comments
27. Amazon accidentally spent $1.8M using Claude for a menial coding task, went (www.tomshardware.com)
    5 points by sbulaev 21 days ago | 1 comments
28. The task is not the job (www.siliconcontinent.com)
    5 points by adletbalzhanov 22 days ago | 1 comments
29. What Has Happened to Taste? (www.esquire.com)
    5 points by acmnrs 23 days ago | 1 comments
30. The poets trying to give AI taste (www.newstatesman.com)
    5 points by paulpauper about 9 hours ago | discuss