| I accidentally turned LLM memory into program analysis HN thread ↗ |
302 |
84 |
LLM |
28 AUG 2026 |
| OCR It – pull text out of un-copyable documents for your LLM HN thread ↗ |
139 |
35 |
LLM |
24 AUG 2026 |
| My agent.md to improve LLM-assisted code quality HN thread ↗ |
410 |
175 |
LLM |
23 AUG 2026 |
| Why your local LLM feels dumber than it is HN thread ↗ |
417 |
171 |
LLM |
22 AUG 2026 |
| Clean up Claude 5's token vomit with a separate LLM HN thread ↗ |
302 |
291 |
LLM |
20 AUG 2026 |
| What happens when an LLM never sees material beyond fifth grade? HN thread ↗ |
244 |
209 |
LLM |
16 AUG 2026 |
| GenRec: Towards LLM-Native Recommendation at Netflix HN thread ↗ |
32 |
54 |
LLM |
15 AUG 2026 |
| Show HN: ThoughtDAG – An editable context graph for LLM conversations HN thread ↗ |
134 |
61 |
LLM |
15 AUG 2026 |
| A Contract-Grade Verifier for LLM-Generated GPU Kernels HN thread ↗ |
46 |
0 |
LLM |
14 AUG 2026 |
| Apple Silicon and macOS VMs: 11–16× Faster LLM Inference with Llama.cpp HN thread ↗ |
305 |
43 |
LLM |
11 AUG 2026 |
| Stealing Reasoning Traces from Proprietary LLM APIs HN thread ↗ |
692 |
302 |
LLM |
11 AUG 2026 |
| Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots HN thread ↗ |
524 |
176 |
LLM |
10 AUG 2026 |
| Humanising LLM Outputs Is Dumb HN thread ↗ |
228 |
174 |
LLM |
10 AUG 2026 |
| Show HN: A tiny LLM running at 21,000 tok/s on a $250 FPGA (Live Demo) HN thread ↗ |
76 |
30 |
LLM |
10 AUG 2026 |
| I won't read LLM authored fiction HN thread ↗ |
72 |
112 |
LLM |
7 AUG 2026 |
| Inside vLLM: Anatomy of a High-Throughput LLM Inference System (2025) HN thread ↗ |
149 |
10 |
LLM |
6 AUG 2026 |
| Born Against, or why hobby programming communities are against LLM usage HN thread ↗ |
424 |
509 |
LLM |
5 AUG 2026 |
| Rust-lang/rust is adopting an LLM policy HN thread ↗ |
116 |
71 |
LLM |
5 AUG 2026 |
| Zero-Mem: Zero-Token Memory Operations for LLM Agents HN thread ↗ |
101 |
13 |
LLM |
5 AUG 2026 |
| SQLite Critical CVEs or LLM Slop? HN thread ↗ |
723 |
373 |
LLM |
3 AUG 2026 |
| Prevent cognitive debt by manually retyping LLM-generated code HN thread ↗ |
533 |
439 |
LLM |
3 AUG 2026 |
| Don't credit the LLM HN thread ↗ |
35 |
48 |
LLM |
2 AUG 2026 |
| Predictive Speculative KV Replication for Bursty LLM Inference HN thread ↗ |
41 |
4 |
LLM |
31 JUL 2026 |
| Everyone is building LLM routers, we deprecated ours HN thread ↗ |
130 |
85 |
LLM |
31 JUL 2026 |
| LLM Honeypot HN thread ↗ |
384 |
107 |
LLM |
29 JUL 2026 |
| Don't ask an LLM for a confidence score HN thread ↗ |
90 |
35 |
LLM |
28 JUL 2026 |
| Truth is not a direction: a Tarski attack on LLM probes HN thread ↗ |
107 |
79 |
LLM |
27 JUL 2026 |
| Becoming a Research Engineer at a Big LLM Lab HN thread ↗ |
53 |
21 |
LLM |
25 JUL 2026 |
| LLM Usage in Debian: Three Proposals HN thread ↗ |
213 |
212 |
LLM |
25 JUL 2026 |
| Running a 28.9M parameter LLM on an $8 microcontroller HN thread ↗ |
279 |
70 |
LLM |
25 JUL 2026 |
| Hetzner is working on LLM Inference HN thread ↗ |
153 |
87 |
LLM |
24 JUL 2026 |
| Anthropomorphism in Children's Interactions with LLM Chatbots HN thread ↗ |
33 |
43 |
LLM |
22 JUL 2026 |
| Codeberg: ToU extension to prohibit LLM-extrusions HN thread ↗ |
49 |
77 |
LLM |
22 JUL 2026 |