CLIP by OpenAI
Hacker ApprovedRanked 3 of 8 embedding models by recommenders
Recommended for image embeddings and similarity search; it is open source and good at object recognition. Critics say it struggles beyond objects and lacks temporal understanding.
Recommended for image embeddings and similarity search; it is open source and good at object recognition. Critics say it struggles beyond objects and lacks temporal understanding.
15 people gave an opinion
- recommend it
- 10
- criticize it
- 5
- approval share
- 67%
Recommended in 6 of 13 months
- November 2025: recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 10 people recommend itNeeds 10 or more, met.
- 2 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 6 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Image similarity search results
“Using a CLIP or Dino v2 model to produce image embeddings would probably improve the similarity search a lot”
Comment from 7 Jan 2026 on Hacker News “CLIP should give the images that actually look similar.”
Comment from 7 Jan 2026 on Hacker News Open source image encoding
“CLIP is an open source model used for image encoding”
Comment from 29 Aug 2026 in “Our decision on Cursor following its acquisition by SpaceX” “CLIP was one of first of Image-text type models”
Comment from 29 Nov 2025 in “Hachi: An Image Search Engine” Small specialised model worth using
“What I'm actually excited about in AI are smaller specialised things like whisper, CLIP, SAM, etc.”
Comment from 31 May 2026 in “Ask HN: What Is the State of App Development in 2026?” “CLIP[1] for actions! Very cool.”
Comment from 24 Sep 2026 in “Contrastive Language Models”
What people warn about
Each mark is one comment
Weak beyond object recognition
“CLIP is really good at object definitions, but struggles at pretty much everything else”
Comment from 27 Aug 2026 in “Getting video models to learn better, faster” “CLIP here was essentially useless”
Comment from 25 Nov 2025 in “FLUX.2: Frontier Visual Intelligence”
Other embedding models people recommend
The four most recommended other embedding models, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| EmbeddingGemma | 27 | 4 | 87% | 3 | — | — |
| Ternlight | 17 | 3 | 85% | 1 | — | — |
| CLIP by OpenAIThis page | 10 | 5 | 67% | 6 | — | Approved |
| Gemini Embedding 2 | 9 | 3 | 75% | 3 | — | — |
| Qwen3-Embedding | 8 | 1 | 89% | 4 | — | — |
What people said
14 of the 15 comments that mention it, newest first. Each links to the original comment.
“CLIP[1] for actions! Very cool.”
“CLIP is an open source model used for image encoding”
“avoid some of the spurious semantic correlation CLIP has”
“CLIP is really good at object definitions, but struggles at pretty much everything else”
“What I'm actually excited about in AI are smaller specialised things like whisper, CLIP, SAM, etc.”
“CLIP should give the images that actually look similar.”
“Using a CLIP or Dino v2 model to produce image embeddings would probably improve the similarity search a lot”
“though it lacks temporal understanding so you have to do the scene analysis yourself”
“CLIP was one of first of Image-text type models”
“Of course CLIP would be otherwise the other option than a big llm-vl one.”
“CLIP here was essentially useless”
“the weird choice to use CLIP and T5 in the original FLUX”
“Which in my experience is indeed quite effective (and easy/fast).”
“they do a fairly decent job as long as you have good data and know what you're doing”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.