Answer: Aider warns that it may not work well with less capable models because such models are usually not capable of properly returning "code edits", so aider can't edit your files and commit the changes. Models weaker than GPT 3.5 may have problems working well with aider. Status: Confirmed Entry: tool/aider/models/capable-model-warning Revision: 1 Digest: sha256:404459db94213b0d (changes whenever the content changes) Timeline: Created: 2026-11-13T02:56:23Z Last changed: 2026-11-13T02:56:23Z Last verified: 2026-11-20T11:42:50Z Next check: 2026-11-21T11:42:50Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of reason | the model isn’t capable of properly returning “code edits” | [1] | 2026-11-20 warning | aider may not work well with less capable models | [1] | 2026-11-20 weakest model threshold | GPT 3.5 | [1] | 2026-11-20 Sources: [1] Aider. "aider.chat/docs/llms.html". https://aider.chat/docs/llms.html Role: primary. Accessed: 2026-11-20T11:42:50Z Quote: "this is usually because the model isn’t capable of properly returning “code edits”." (Supports: reason) Quote: "Be aware that aider may not work well with less capable models." (Supports: warning) Quote: "Models weaker than GPT 3.5 may have problems working well with aider." (Supports: weakest model threshold) Published: 2026-04-25T16:45:23Z Snapshot SHA-256: 633cac70a9392f7e7e62e1520194fe235861fa69578e3fc66c2d921d1def55a4 (captured 2026-11-13T02:56:22Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. On this check the text of [1] was unchanged since 2026-11-13T02:56:23Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T11:42:50Z. No independent second source is configured for this entry Last successful check: 2026-11-20T11:42:50Z Last attempt: 2026-11-20T11:42:50Z Notes and limitations: Extracted automatically from a single official source (section "Use a capable model"). Related: https://latestn.com/tool/aider/models/change-main-model How do I change the main model Aider uses? https://latestn.com/tool/aider/models/choose-llm-model How do I choose or switch the LLM model Aider uses? https://latestn.com/tool/aider/models/cohere-recommended-model Which Cohere model does Aider recommend for coding? https://latestn.com/tool/aider/models/best-models-recommendation Which LLMs does Aider recommend as the best models to use? https://latestn.com/tool/aider/models/browser-ui-supported-models Which LLM models work well with Aider's browser UI? https://latestn.com/tool/aider/models/builtin-model-aliases What built-in model aliases does Aider provide? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-13T02:56:23Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/aider/models/capable-model-warning/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/aider/models/capable-model-warning POST: https://latestn.com/dispute/tool/aider/models/capable-model-warning with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/aider/models/capable-model-warning?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). Why does Aider warn that I should use a more capable model? Revision 1, last verified 2026-11-20T11:42:50Z. https://latestn.com/tool/aider/models/capable-model-warning (accessed 2026-11-21T09:53:21Z). @misc{LatestN_tool_aider_models_capable_model_warning_r1, title = {Why does Aider warn that I should use a more capable model?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/aider/models/capable-model-warning}}, note = {Revision 1; digest sha256:404459db94213b0d; last verified 2026-11-20T11:42:50Z; accessed 2026-11-21T09:53:21Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/aider/models/capable-model-warning