3.3K views · 24 likes · 0 reposts (at collection)
Perplexity develops JOLT, a post-training method that uses one model as teacher and student
- Who
- Perplexity
- What
- developed JOLT, a post-training method where one model acts as both teacher and student
What happened
New research: We developed JOLT, a post-training method where one model acts as both teacher and student, with the teacher trained to give feedback the student can use. On MATH, it matched GRPO's accuracy with 6.5x fewer training tokens.
Links in the post: 2The story so far
Perplexity developed JOLT, a post-training method that uses one model as both teacher and student, and said it matched GRPO’s accuracy on MATH with 6.5x fewer training tokens. In JOLT, the teacher is trained to provide feedback the student can use. The reported efficiency result applies specifically to the MATH benchmark.
Keep reading
Latest daily · Issue 28Mistral AI releases Voxtral 3 speech models and a voice agent SDKTrending now
- 1Mistral and NVIDIA Announce Industrial Engineering AI Collaboration and Open Benchmarks
- 2OpenAI Models and Codex Workflows Coming to Google Cloud, With Reports Differing on Availability
- 3Mistral Releases Voxtral 3 Speech Models, Voice Agents API and LiveKit-Based SDK
- 4PHP releases security updates after OpenAI says its models helped researchers find critical flaws
Tomorrow at 08:00, a briefing like this arrives in your inbox.
The same kind of briefing as the one above: a few stories worth reading. Free. Mail starts after you confirm, and every letter has a one-click unsubscribe. Read a past issue · 2026-10-21