I deleted slow, expensive LLM turns in coding agents with Jev
Mean of 3 A/B runs on a real code-change prompt — everything normalized to baseline (lower is better). It all started with hating, a week before Jev I hate waiting and love shipping fast. Yet, coding agents feedback loop excel at making you wait.
- ▪Mean of 3 A/B runs on a real code-change prompt — everything normalized to baseline (lower is better).
- ▪It all started with hating, a week before Jev I hate waiting and love shipping fast.
- ▪Yet, coding agents feedback loop excel at making you wait.
Hacker News (AI / LLM) files mainly under ai. We currently carry 6,022 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 | DecisionKit |
| Canonical URL | https://tawfeks.github.io/decisionkit/ |
| Publication time | Tue, 22 Sep 2026 15:44:48 +0000 |
| Retrieval time | 2026-09-22T15:48:50.849Z |
| Last seen | 2026-09-22T15:48:50.849Z |
| 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 | S1GpwSNi8CSb · 1 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
Mean of 3 A/B runs on a real code-change prompt — everything normalized to baseline (lower is better). It all started with hating, a week before Jev I hate waiting and love shipping fast. Yet, coding agents feedback loop excel at making you wait. 23 mins is almost the bare minimum for anything meaningful built with coding agents. While writing the article, this is the coding agent going for 2m 41s at 77 t/s for just showing link preview and two options for sharing (one image and one for article) in this page: Even with the wait, I’m able to ship faster, especially small tweaks. Good! But those need running tests and building, another 3 mins to 15 mins added per push.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at DecisionKit.
Discussion
0 commentsMore from DecisionKit
