Ask HN: What LLM models are you using and why?
The post on Hacker News asks users to share which large language models they are currently using and their reasons for preference. The author notes a shift from Opus 4.6 to GPT-5.5 for work due to improved consistency and writing style, despite Opus 4.7's stronger coding performance. For personal projects, the author highlights DeepSeek V4 for its cost-effectiveness and large 1M token context window, though it requires additional tooling for optimal results.
- ▪The author now uses GPT-5.5 more than Opus 4.7 for work due to its consistency and less tiresome writing style.
- ▪Previously, Opus 4.6 was the primary model, with GPT-5.4 used only for second opinions and Grok for experimental 'chaos' inputs.
- ▪DeepSeek V4 is being tested for personal projects because of its 1M token window and favorable cost-to-quality ratio.
- ▪The author notes that DeepSeek V4 is weaker at one-shot tasks but performs well with linter and static-analysis support.
- ▪Users are invited to share their use of reranking, embedding models, or other tools to enhance LLM performance.
2 outlets in our directory ran this story, first to last over 21 hours. All of the coverage we found sits in one bucket: centre. That one-sidedness is itself worth noticing.
- ▪ LLM providers are retiring models faster than you can migrate — DEV.to (Top)
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,279 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Ycombinator |
| Canonical URL | https://news.ycombinator.com/item?id=48166147 |
| Publication time | Sun, 17 May 2026 04:57:21 +0000 |
| Retrieval time | 2026-05-17T05:08:58.480Z |
| Last seen | 2026-05-17T05:08:58.480Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | lWkx_6FvEQmV · 2 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Hello, HN!I'm wondering what y'all are using for your daily driver these days and why?I've found myself using GPT-5.5 more than Opus 4.7 for work; which, has been a pretty big reversal. Previously, I was using Opus 4.6 for everything, and GPT-5.4 was only ever in the picture to provide a second opinion (with Grok a distant 3rd only when I wanted to throw some "chaos" into the mix). The reason I've personally pivoted, is I've found GPT-5.5 to be a bit more consistent, predictable, and tends to write in a way I find less tiresome (even if the code isn't quite as good as Opus 4.7).For personal projects, I've started experimenting with DeepSeek V4 and have been pretty blown away by it because of it's cost to quality and I've found the 1M token window to be incredibly helpful for long-running…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Ycombinator.