occamschainsaw

There’s a fascinating story about S Chandrasekhar (of Chandrasekhar limit fame) driving 100 miles to teach him every week. Teaching two students, the professor got a Nobel prize and the two students got a Nobel prize.

“ One story in particular illustrates Chandrasekhar's devotion to his science and his students. In the 1940s, while he was based at the University's Yerkes Observatory in Williams Bay, Wis., he drove more than 100 miles round-trip each week to teach a class of just two registered students. Any concern about the cost-effectiveness of such a commitment was erased in 1957, when the entire class -- T.D. Lee and C.N. Yang -- won the Nobel Prize in physics.”

Source: https://chronicle.uchicago.edu/951012/chandra.shtml

There’s already some work looking into this[1]. The authors add invisible prompts in papers/grants to embed watermarks in reviews and then show that they can detect LLM generated reviews with reasonable accuracy (more than chance, but there’s no 100% detection yet).

[1] Rao et al., Detecting LLM-Generated Peer Reviews https://arxiv.org/pdf/2503.15772

Even o3 can't figure out the naming scheme. When asked to generate names that would be easier to use by non-technical people, it assumed o3 and o4 are the smallest models:

``` Below is one straightforward, user-friendly approach you could adopt. It keeps two dimensions only—generation and tier—and reserves an optional “optimisation” suffix for special-purpose variants (e.g. vision, coding, long-context).

⸻

1. Core conventions

Element Purpose Example values Generation Major architectural release. Keep a whole number; use “.1”, “.2”… for mid-cycle improvements. 4, 4.1, 4.5 Tier Rough capability / cost band, easy to interpret. Lite, Standard, Pro, Ultra Suffix (optional) Special optimisation or domain specialisation. -LongCtx, -Vision, -Code

Why this works • No ambiguous letters or numerics – “o3” can be read as “03” or “oz”; avoid that entirely. • Self-explanatory language – non-technical users recognise “Lite” versus “Pro” instantly. • Scalable – new minor rev? bump the generation (4.2). Need a cheaper size? add a Nano tier without disturbing the rest.

⸻

2. Applying it to your current list

Current name Proposed new name Rationale GPT-4o GPT-4 Standard Baseline flagship of the 4-series. o3 GPT-4 Lite Same generation, lowest tier. o4-mini GPT-4 Lite+ (or GPT-4 Lite LongCtx if that’s the point) Indicates “Lite” family but a bit more capable; “+” or a suffix clarifies how. o4-mini-high GPT-4 Standard LongCtx (or GPT-4 Lite Pro) Pick one dimension: either it’s still “Lite” but higher context, or it has moved into “Standard”. GPT-4.5 GPT-4.5 Standard Mid-cycle architectural upgrade, default tier. GPT-4.1 GPT-4.1 Standard Ditto. GPT-4.1-mini GPT-4.1 Lite Same generation, smaller/cheaper option.

⸻

3. Quick style guide for future models 1. Stick to two words (or two words + optional suffix) GPT-5 Pro, GPT-5 Lite-Vision – still readable at a glance. 2. Reserve extra punctuation for special cases only Hyphens or the “+” symbol should signal meaning, not be decorative. 3. Publish a public matrix A small table in docs or the dashboard that maps Generation × Tier → context length, cost, latency eliminates guesswork.

⸻

One-line summary

GPT- [-Specialisation] keeps names short, descriptive and future-proof—so even non-technical users can tell instantly which model suits their needs. ```

o4-mini? It is a rumored model building up on o3, and different from 4o-mini. Sorry, their naming scheme is a mess. Would be cool if you do have o4-mini access though.

https://www.theverge.com/news/646458/openai-gpt-4-1-ai-model