Hackernews posts about LLVM-mca

1. 01
   

   newShow HN: Liquid Inference – auto-routing to competitive LLM marketplaceliquidinference.ai

   ▲ 4chairmanlee828ddiscusssavesaved
2. 02
   

   newMathMixup: Boosting LLM Mathematical Reasoning via Curriculum and Decompositionarxiv.org

   ▲ 1wslh10ddiscusssavesaved
3. 03
   

   newIlluminating the processor core with LLVM-mcaabseil.io

   ▲ 68ckennelly327d💬 5savesaved
4. 04
   

   newPerformance Debugging with LLVM-mca: Simulating the CPUjohnnysswlab.com

   ▲ 33signa11495d💬 14savesaved
5. 05
   

   newLLVM-Mca – LLVM Machine Code Analyzerllvm.org

   ▲ 2BiraIgnacio678d💬 1savesaved
6. 06
   

   newPerformance Debugging with LLVM-mca: Simulating the CPUjohnnysswlab.com

   ▲ 2todsacerdoti612ddiscusssavesaved
7. 07
   

   newLLVM-Mca – LLVM Machine Code Analyzerllvm.org

   ▲ 1tanelpoder555ddiscusssavesaved
8. 08
   

   newMachine Scheduler in LLVM – Part IImyhsu.xyz

   ▲ 31mshockwave370ddiscusssavesaved
9. 09
   

   newMachine Scheduler in LLVM – Part Imyhsu.xyz

   ▲ 5matt_d416d💬 2savesaved
10. 10
    

    newMachine Scheduler in LLVM – Part IImyhsu.xyz

    ▲ 3matt_d369ddiscusssavesaved
11. 11
    

    newMachine Scheduler in LLVMmyhsu.xyz

    ▲ 1mshockwave417ddiscusssavesaved
12. 12
    

    newEuroLLM: LLM made in Europe built to support all 24 official EU languageseurollm.io

    ▲ 773NotInOurNames374d💬 606savesaved
13. 13
    

    newDon’t let an LLM make decisions or execute business logicsgnt.ai

    ▲ 325petesergeant585d💬 169savesaved
14. 14
    

    newThe insecure evangelism of LLM maximalistslewiscampbell.tech

    ▲ 251todsacerdoti297d💬 280savesaved
15. 15
    

    newThe industry structure of LLM makerscalpaterson.com

    ▲ 159paulpauper710d💬 127savesaved
16. 16
    

    newStanisław Lem foretold the current LLM mania in 1964nibblestew.blogspot.com

    ▲ 28latexr67ddiscusssavesaved
17. 17
    

    newOur workplace LLM mass delusionblog.avas.space

    ▲ 24birdculture148d💬 2savesaved
18. 18
    

    newAsk HN: Why are LLM's made intentionally non-deterministic?

    ▲ 5mojuba305d💬 5savesaved
19. 19
    

    newLLM makes decisions to raise its training scores, and ignore user directivesjoinhandshake.com

    ▲ 4guardiangod39d💬 1savesaved
20. 20
    

    newShow HN: Parse LLM Markdown streams incrementally on the server or clientgithub.com

    ▲ 4nayajunimesh176d💬 1savesaved
21. 21
    

    newOur workplace LLM mass delusionblog.avas.space

    ▲ 4speckx149ddiscusssavesaved
22. 22
    

    newA $537 Local LLM Machine (2025)blog.lewman.com

    ▲ 3turtleyacht57ddiscusssavesaved
23. 23
    

    newLLM Margin Labgithub.com

    ▲ 3flurly108ddiscusssavesaved
24. 24
    

    newDiffusion LLM may make most of the AI engineering stack obsolete

    ▲ 3victorpiles99240ddiscusssavesaved
25. 25
    

    newShow HN: LLM-Mafia-Game: AI Models Competing in Mafia Matchesgithub.com

    ▲ 3uncanny_guzus609ddiscusssavesaved
26. 26
    

    newShow HN: Vibe HTTP, a LLM masquerading as a HTTP servervibe.ef.je

    ▲ 2bangoose495d💬 3savesaved
27. 27
    

    newIncrementally parsing LLM Markdown streams on server/clientgithub.com

    ▲ 2nayajunimesh245d💬 2savesaved
28. 28
    

    newShow HN: Word Wizardry – Dijkstra-powered sentences, crafted from LLM magicgithub.com

    ▲ 2modinfo315d💬 1savesaved
29. 29
    

    newI rebuilt the Auth0 Activity Page with webhooks and some LLM magicwww.tinybird.co

    ▲ 2alrocar660d💬 1savesaved
30. 30
    

    newPeer review in the LLM (mania) agewww.humprog.org

    ▲ 2pcfwik43ddiscusssavesaved
31. 31
    

    newCan an LLM make a feature-length movie on its own?www.lesswrong.com

    ▲ 2mchinen79ddiscusssavesaved
32. 32
    

    newThe Scraping Wiki: An LLM-maintained knowledge base indexing 400+ articlesgithub.com

    ▲ 2PigiVinci83198ddiscusssavesaved

· edit