Hackernews posts about Grok 4 Fast

1. 01
   

   newShow HN: A local memory that Claude Code, Codex (and your fav agent) shareonadit.com

   ▲ 1crog8ddiscusssavesaved
2. 02
   

   newGrok 4 Fast now has 2M context windowdocs.x.ai

   ▲ 194hereme888363d💬 281savesaved
3. 03
   

   newGrok 4 Fastx.ai

   ▲ 96meetpateltech413d💬 76savesaved
4. 04
   

   newGemini tops App Store; Grok 4 Fast ships; ChatGPT gets harder to tricklightcapai.medium.com

   ▲ 1WASDAai418d💬 1savesaved
5. 05
   

   newShow HN: AI Paul Grahamwww.paulgraham-nia.com

   ▲ 4arlanrakh335d💬 5savesaved
6. 06
   

   newShow HN: Prompt2pwn – CTF Automated Solvergithub.com

   ▲ 1bigEnotation255ddiscusssavesaved
7. 07
   

   newGrok 4.20 brings minimal improvements over Grok-4.1-fastaibenchy.com

   ▲ 2XCSme239d💬 1savesaved
8. 08
   

   newGrok 4.1 Fast Is Now Available in Puter.jsdeveloper.puter.com

   ▲ 2ent101351d💬 1savesaved
9. 09
   

   newGrok 4.1 Fast and Agent Tools APIx.ai

   ▲ 1meetpateltech352ddiscusssavesaved
10. 10
    

    newShow HN: Get GPT-5.2, Grok-4.1-fast, KimiK2.5 and more LLMs at half the costfrogapi.app

    ▲ 2vnhc251ddiscusssavesaved
11. 11
    

    newShow HN: Watch LLMs play 21,000 hands of Pokerpokerbench.adfontes.io

    ▲ 36jazarwil302d💬 19savesaved
12. 12
    

    newShow HN: ACE – A dynamic benchmark measuring the cost to break AI agentsfabraix.com

    ▲ 9zachdotai215d💬 3savesaved
13. 13
    

    newShow HN: Pencil Puzzle Bench – LLM Benchmark for Multi-Step Verifiable Reasoningppbench.com

    ▲ 5bluecoconut248ddiscusssavesaved
14. 14
    

    newAsk HN: Former grok-code-fast-1 users, what coding model are you using now?

    ▲ 2whycombinetor209d💬 3savesaved
15. 15
    

    newShow HN: OpenClaw Arena – Benchmark models on real tasks, rank by perf and costapp.uniclaw.ai

    ▲ 2skysniper220ddiscusssavesaved
16. 16
    

    newShow HN: Beads Viewer (Bv)github.com

    ▲ 4eigenvalue339ddiscusssavesaved
17. 17
    

    newAsk HN: Anybody else enjoying Cursor's native (xAI) models?

    ▲ 1manlymuppet32d💬 2savesaved
18. 18
    

    newAsk HN: Cursor (LLM) Costs

    ▲ 1anonyfox299d💬 2savesaved
19. 19
    

    newShow HN: Two-Dimensional Phase Portrait Plotterharaldrevery.com

    ▲ 1hrldrvry265ddiscusssavesaved
20. 20
    

    newGrok is a surprisingly good automated theorem prover

    ▲ 3henryrobbins00107d💬 1savesaved
21. 21
    

    newI am building a collaborative coding agent

    ▲ 2brainless348ddiscusssavesaved
22. 22
    

    newShow HN: Cactus Hybrid: We taught Gemma 4 to know when it's wronggithub.com

    ▲ 191HenryNdubuaku107d💬 44savesaved
23. 23
    

    newShow HN: Completely free Claude Sonnet 4.5, supported by contextual ads

    ▲ 5namanyayg365d💬 2savesaved
24. 24
    

    newShow HN: MyStats – AI-Powered Self-Discovery with Gemini/OpenAI/Claude/Grokgithub.com

    ▲ 2kyounsgookim309ddiscusssavesaved
25. 25
    

    newShow HN: I'm giving Claude Sonnet 4.5 for free to those who need it with ads

    ▲ 1namanyayg364d💬 3savesaved
26. 26
    

    newShow HN: Pluely – open-source alternative to Cluely (~10MB, Always On Display)github.com

    ▲ 7truly_sn445d💬 5savesaved
27. 27
    

    newAsk HN: How high is the bar for AGI? what problems are "AGI-complete"?

    ▲ 2adinhitlore423d💬 3savesaved
28. 28
    

    newI made a prompt framework that makes LLMs stop hedging and speak straight

    ▲ 2DrRockzos334d💬 1savesaved
29. 29
    

    newTell HN: Forget selectors and screenshots. The agentic web lives in your shell

    ▲ 2keepamovin144ddiscusssavesaved
30. 30
    

    newCreating "Hello World" executable bytes for LLMs is so hard?

    ▲ 1artificiology610d💬 3savesaved
31. 31
    

    newAsk HN: What is the best bang for buck budget AI coding?

    ▲ 1LowResBudget263d💬 2savesaved

· edit