AI · អត្ថបទ
Anthropic Says Good Agent Memory Depends on What AI Forgets
The Decoder ·

មើលត្រួសៗ
Anthropic studied how Claude keeps knowledge across sessions without changing the model itself. Its tests suggest that short, selective notes work better than huge archives, and that having Claude review its notes later can fix errors.
ចំណុចសំខាន់ៗ
- Claude saves notes to a folder it can read later, so knowledge carries over between sessions.
- In a Pokémon Red test, an older Claude model saved hundreds of files and got stuck reorganizing them, while a newer model kept a few useful notes and earned more badges.
- A feature called Dreaming lets Claude check its notes against past transcripts, which helped it catch a wrong landmark note.
- Anthropic also reported that a wiki combined with search answered multi-document legal questions better than search alone, though these results come only from Anthropic.
ហេតុអ្វីវាសំខាន់
Anyone using AI agents on long projects needs memory that stays accurate, and this research shows that storing less but better may work best.
ប្រភពដើម
Anthropic says the key to agent memory is knowing what to forget, not how much to store
The Decoder · Nov 17, 00:25 KST
Read on The Decoder ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to The Decoder.
បន្ថែមពីវិស័យនេះ
- Google Drops Search Button and Adds AI Sidebar to Its Search Homepage
Google has officially rolled out a redesigned desktop search homepage after a successful test. The Google Search button next to the search bar is gone, and a row of AI buttons now sits under the bar. Logged-in users also get a sidebar showing their recent AI Mode conversations.
Ars Technica · Nov 21, 06:58 KST - Meta Rethinks 2030 Net-Zero Goal as AI Data Center Emissions Hit Record High
Meta's 2026 sustainability report said the company is re-evaluating its 2030 net-zero goal. Its emissions rose about 40 percent from 2024 to 2025, the largest jump among the big US tech companies.
Ars Technica · Nov 21, 06:47 KST - Anthropic Mathematician Says Claude Helped Crack the Riemann Hypothesis
Levent Alpöge, a mathematician at Anthropic, says he has proved the Riemann hypothesis with help from Claude, Anthropic's AI system. Instead of a regular math paper, he posted a four-page note and linked to computer code that he says checks the result. The claim still needs to be verified.
The New York Times · Nov 21, 06:47 KST - Designers Say Ssense's Website Shows Their Clothes Inaccurately
Designer Reese Cooper noticed his RCOS puffer coat looked distorted on the luxury retailer Ssense's website, with a chest hook drawn far too large. Ssense said some site images came from a "virtual try-on" program, though it would not say whether that program uses AI.
The New York Times · Nov 21, 06:16 KST