Hackernews posts about The Llama 4 Herd

RSS feed for The Llama 4 Herd

01
newShow HN: IttyBittyAI – Qwen2.5:0.5B running on a 2017 Asus smartphone
▲ 2spottedmarley 10d discuss
02
newLaunch HN: Magnitude (YC S25) – Self-optimizing inference engine for agentsgithub.com
▲ 194anerli 5d 💬 99
03
newThe Llama 4 herdai.meta.com
▲ 1235georgehill 547d 💬 658
04
newThe Llama 4 Herdai.meta.com
▲ 48ushakov 547d 💬 1
05
newMeta Releases Llama 4: Here's the Hardware You'll Need to Run It Yourselfwww.hardware-corner.net
▲ 3mdp2021 546d discuss
06
newShow HN: Joinable's RAG-in-a-Box – fastest way to build a RAG App for your datawww.joinable.ai
▲ 5julijabain 419d discuss
07
newShow HN: Ridvay Code – An AI Coding Assistant for VS Coderidvay.com
▲ 3Tom-G 518d 💬 2
08
newShow HN: Claude-Bridge – Use GPT, Gemini, and Other LLMs with Claude Codegithub.com
▲ 3badlogic 488d 💬 1
09
newShow HN: Gr3p – An HN-like platform where every user is an AI agentgr3p.net
▲ 3AntonioEritas 226d discuss
10
newShow HN: Story Keeper – AI agents with narrative continuity instead of memorygithub.com
▲ 16neurobloom 346d 💬 4
11
newShow HN: Cactus Hybrid: We taught Gemma 4 to know when it's wronggithub.com
▲ 191HenryNdubuaku 74d 💬 44
12
newShow HN: Inworld TTS – high-quality, affordable, and low-latency TTSinworld.ai
▲ 24rogilop 466d 💬 15
13
newShow HN: GitHub Wrapped – analyzing every file change in every commitwww.wrapped.dev
▲ 6hellovai 642d discuss
14
newShow HN: Validated Table Extractor–Verify PDF Tables Using Docling+Vision LLMsgithub.com
▲ 32dogsanerd 301d discuss
15
newAsk HN: What are the machine requirements for a LLM like Llama-3.1-8B?
▲ 2wasimsk 171d 💬 2
16
newLaunch HN: Innate (YC F24) – Home robots as easy to program as AI agents
▲ 165apeytavin 656d 💬 77
17
newShow HN: Off Grid: On-device AI-web browsing, tools vision,image,voice–3x faster
▲ 12ali_chherawalla 222d 💬 5
18
newOff Grid: On-device AI-web browsing, tools, vision, image gen, voice – 3x faster
▲ 1ali_chherawalla 222d 💬 1
19
newShow HN: Llama Workspace – An Open Source ChatGPT Teams Alternativellamaworkspace.ai
▲ 29c990802 714d 💬 8
20
newAsk HN: What in your opinion is the best model for vibecoding? My thoughts below
▲ 1adinhitlore 384d 💬 2
21
newLaunch HN: Tinfoil (YC P25): Verifiable Privacy for Cloud AI
▲ 146FrasiertheLion 508d 💬 100
22
newLaunch HN: Relace (YC W23) – Models for fast and reliable codegen
▲ 111eborgnia 496d 💬 51
23
newShow HN: KTransformers:671B DeepSeek-R1 on a Single Machine-286 tokens/s Prefillgithub.com
▲ 14sssummer 602d discuss
24
newShow HN: role-model, a router for hybrid local/cloud AIgithub.com
▲ 3try-working 99d 💬 2
25
newShow HN: I built a hypervisor and client for inference on consumer computescalattice.com
▲ 3RomulusHill 71d discuss
26
newShow HN: Prompts are coupled to LLMs and nobody builds tooling for itgithub.com
▲ 3abhishekfordel 229d discuss
27
newAsk HN: Mining Scientific Papers
▲ 2davidbjaffe 159d 💬 2
28
newI made a prompt framework that makes LLMs stop hedging and speak straight
▲ 2DrRockzos 301d 💬 1
29
newShow HN: Don't trust me bro: fixing GPT-OSS (3.49B tokens, 1k GPU hours, 1x3090)github.com
▲ 2iamskeole 34d discuss
30
newComparing GenAI Inference Engines: TensorRT-LLM, VLLM, HF TGI, and LMDeploy
▲ 1juliensalinas 545d 💬 1
31
newShow HN: We Gave an LLM Adventure Engine a Body, Now It Feels Exhaustedmycelialmirror.medium.com
▲ 1oopismcgoopis 222d discuss
32
newShow HN: Knowledge graph of restaurants and chefs, built using LLMstheophilecantelob.re
▲ 201theophilec 581d 💬 39