Show HN: Gave Claude Code ADHD.. Now it thinks 3x better
A new method called ADHD has been introduced to enhance the ideation capabilities of large language models. This approach allows for parallel divergent thinking, producing a wider range of creative solutions rather than defaulting to common responses. In evaluations, ADHD significantly outperformed traditional methods in terms of novelty and breadth of ideas.
- ▪ADHD prevents premature convergence by generating multiple divergent branches before converging on the best ideas.
- ▪The method was tested against a single-shot baseline and won 5 out of 6 evaluations on open-ended engineering problems.
- ▪ADHD improves metrics such as novelty, breadth, and trap detection compared to existing methods.
Hacker News (Show HN) files mainly under programming. We currently carry 68 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 | Github |
| Canonical URL | https://adhdstack.github.io/ |
| Publication time | Wed, 27 May 2026 12:00:38 +0000 |
| Retrieval time | 2026-05-27T12:07:59.258Z |
| Last seen | 2026-05-27T12:07:59.258Z |
| 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 | Almo1n0X5Bor |
| 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
Preprint · v0.1 · 2026-05-25 ADHD: Parallel Divergent Ideation for Coding Agents Tree-of-thought with cognitive-frame branching, generator–critic separation, and pruning. Udit Akhouri Raj · github.com/UditAkhourii/adhd Code Evals Source skill npm Abstract Large language model agents exhibit premature convergence: when asked to ideate on an open-ended design problem they default to the first plausible candidate and polish it, producing competent but forgettable output. We introduce ADHD, a method that fans out N parallel divergent branches under structurally different cognitive frames (e.g. regulator, speedrunner, biology, $0 budget), with no cross-branch context, then converges via a separate critic pass that scores, clusters, and deepens only the top-K survivors.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Github.
Discussion
0 commentsMore from Github
![Everything is a UOp – reading the deep learning stack behind comma[dot]AI](/img-proxy?url=https%3A%2F%2Fssenthilnathan3.github.io%2Fimages%2Ftinygrad.jpeg&w=320)
