Ted Sanders says model size explains most LLM performance gaps
Bigger models generally cost more per token and recall obscure facts better, even when skill rankings differ.
18
- Mentions · 7d2
- Mentions · 30d4
- All mentions9
- First seenSep 10, 2026
- Last mentioned2d ago
Timeline
9 articles · newest firstOpenAI's Ted Sanders offers a rule for choosing GPT models
He says pick Astra for quality, Sol if somewhat price-sensitive, and Terra or Luna when price matters most.
22
500B Tokens Later: Letting AI Agents Decompile a First-Person Shooter
A team spent about 500 billion tokens orchestrating AI agents to decompile an unnamed shooter.
46
A Series of Unfortunate Events for OpenAI Users
Commentary says OpenAI cut Codex usage and shipped weak GPT-6 models while chasing consumers.
36
OpenAI’s Jev clone could help the frontier lab stop its swarming agents
OpenAI previewed a Decisions API resembling TypeSafe's Jev for fast, cheap classification of agent actions.
55
OpenAI gives Codex reusable cloud environments that work across devices
OpenAI made Codex cloud environments reusable across devices and added CLI, review, and security tools.
62
Gemini can now call businesses for you so you don’t have to wait on hold
Google's AI enables business phone calls via a Pixel 11 feature, allowing users to delegate local business interactions with Gemini while retaining control through a live transcript view.
70
AI performance costs are falling faster than those of any previous technology
AI performance costs are falling faster than any previous technology, with 47% quarterly and 13x annual drops in average costs.
70
Build more natural voice experiences with GPT‑Live‑1 in the API
OpenAI releases GPT-Live-1 in the API, a full-duplex voice model that handles interruptions natively and delegates reasoning to backend models.
72
Appears with
- OpenAIvendor · 8
- OpenAIorganization · 6
- ChatGPTproduct · 3
- Astraai model · 3
- Codexproduct · 3
- Solai model · 3
- GPT-6 Solai model · 3
- Anthropicorganization · 3
- Anthropicvendor · 3
- Terraai model · 3
- Opus 5.5ai model · 2
- o3ai model · 2
- Googleorganization · 2
- Googlevendor · 2
- Claude Codeproduct · 2
- Microsoftorganization · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.