LLM Time Travel Visualization Proposal
I suggest a ‘LLM time travel interface’: providing a chatbot ‘playground’ which runs a new, user-specified, prompt into the best surviving LLM from every year over the recent past, and automatically ranks them by quality and compares the current prompt’s improvement over time to the global improvement over time. This avoids any suspicions about cherrypicking and allows direct comparisons over time. It is difficult to explain to people who have not been using them from the start how remarkable the steady, rapid, broad increase of LLM capabilities has been.
- ▪I suggest a ‘LLM time travel interface’: providing a chatbot ‘playground’ which runs a new, user-specified, prompt into the best surviving LLM from every year over the recent past, and automatically ranks them by quality and compares the cu
- ▪This avoids any suspicions about cherrypicking and allows direct comparisons over time.
- ▪It is difficult to explain to people who have not been using them from the start how remarkable the steady, rapid, broad increase of LLM capabilities has been.
Hacker News (AI / LLM) files mainly under ai. We currently carry 5,995 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 | Hacker News (AI / LLM) |
| Canonical URL | https://gwern.net/blog/2026/llm-timetravel |
| Publication time | Tue, 22 Sep 2026 14:22:59 +0000 |
| Retrieval time | 2026-09-22T14:43:51.627Z |
| Last seen | 2026-09-22T14:43:51.627Z |
| 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 | 5p56YQvsFkDj · 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
LLM Time Travel Visualization Proposal AI scaling Proposal for AI education application: interactive prompt use of the best surviving LLM from each year over the past decade, to dramatize the rapid escalation of capabilities for people who weren’t paying attention. by: Gwern 2026-09-02–2026-09-21 finished certainty: log similar How can we help non-AI specialists understand the speed of LLM progress over the past decade? I suggest a ‘LLM time travel interface’: providing a chatbot ‘playground’ which runs a new, user-specified, prompt into the best surviving LLM from every year over the recent past, and automatically ranks them by quality and compares the current prompt’s improvement over time to the global improvement over time.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Hacker News (AI / LLM).
Discussion
0 commentsMore from Hacker News (AI / LLM)
