cd/entity/Hacker News· home entities Hacker News
grep -l @hacker news /news/*.json | wc -l → 812

Hacker News

mentions 812 type Person page 34/41 feed RSS

// recent coverage 812 mentions

06:12
2026-06-17
byteiota.com
large-language-models

Local LLMs Are Good Now: What Actually Changed in 2026

ML engineer Vicki Boykis's blog post 'Running Local Models is Good Now' hit the top of Hacker News, signaling that local AI models have crossed from hobbyist experiment to genuine developer workflow i…

04:15
2026-06-17
news.ycombinator.com
ai-tools

Ask HN: What are your best Claude hacks?

A Hacker News user asked the community to share their best Claude hacks, highlighting a workflow of uploading research papers to Claude to create a temporary domain expert.…

17:46
2026-06-16
news.ycombinator.com
artificial-intelligence

Ask HN: How do you stay at the bleeding edge of AI tooling?

A Hacker News user asked the community where to find discussions about bleeding-edge AI tooling, expressing frustration with forums where uninformed opinions dominate. The user seeks a community of en…

16:04
2026-06-16
simonwillison.net
large-language-models

Quoting Georgi Gerganov

Georgi Gerganov, creator of llama.cpp, reported that the Qwen3.6-27B model is highly capable for local coding tasks, using it daily on his M2 Ultra and RTX 5090 systems. He noted the model's utility f…

15:39
2026-06-16
news.ycombinator.com
large-language-models

Ask HN: Why are LLMs so bad at board games?

A user on Hacker News reports that large language models consistently fail to understand board game rules, raising concerns about fundamental limitations in AI reasoning. Despite rulebooks being self-…

15:12
2026-06-16
infer0.com
ai-infrastructure

Show HN: Infer0 – do AI apps need subscriptions?

A developer launched Infer0, a service that lets users bring their own AI API keys to applications, aiming to eliminate subscription costs for AI-powered side projects. The platform acts as SSO for AI…

14:16
2026-06-16
byteiota.com
large-language-models

Local LLMs vs Claude for Coding: The 70% Problem

A Hacker News thread on June 16 revealed that local LLMs like Qwen 3.6 35B-A3B handle about 70% of daily coding tasks but fall short on complex multi-file reasoning, creating a gap akin to a junior ve…

13:32
2026-06-16
news.ycombinator.com
large-language-models

Ask HN: How is your company getting cited by ChatGPT?

A Hacker News user asks how companies are getting cited by ChatGPT and AI tools, seeking strategies for small businesses in large markets to become AI references.…

12:39
2026-06-16
news.ycombinator.com
ai-tools

AskHN:How do you handle skill atrophy from using coding agents?

A Hacker News user asks how to prevent skill atrophy when relying on AI coding agents, noting that exclusive use of AI for tasks leads to cognitive decline. The community is invited to share activitie…

12:31
2026-06-16
github.com
ai-agents

Show HN: WebCap – Reusable web capabilities for AI agents

Web-Capability, a local-first browser automation toolkit for AI agents, launched on Hacker News. The tool lets agents inspect browser tabs, run reusable in-page scripts, save workflows for command-lin…

01:09
2026-06-16
byteiota.com
ai-safety

That LinkedIn Job Offer Hid a Backdoor in npm install

A developer received a LinkedIn message from a recruiter at a crypto startup asking to review a GitHub repository before a technical interview. The repository contained a backdoor in npm's prepare scr…

00:00
2026-06-16
tomtunguz.com
large-language-models

5x for Free : The Local Coding Stack

A Hacker News thread reveals that local AI coding models, led by Qwen 3.6 35B-A3B and harness Pi, are increasingly replacing cloud-based tools like Claude and GPT, offering privacy, zero cost, and off…

22:55
2026-06-15
news.ycombinator.com
large-language-models

Ask HN: How much better has Fable been at design, really?

A Hacker News user questions whether Anthropic's Claude Fable model truly excels at UI, design, and game development compared to Claude Opus 4.8, suggesting that many showcased capabilities could be a…

22:32
2026-06-15
build-small-hackathon-llm-fishing.hf.space
large-language-models

Show HN: Fish anything – a chill game using small models

A developer released 'Fish anything', a chill game built using small language models, hosted on Hugging Face Spaces. The project was shared on Hacker News as a Show HN submission.…

← prev page 34 / 41 next →
// co-occurs with top 8 entities
// topics top 6 topics