全部动态

本页 40 条
10月13日 周二
Hacker News AI51

Show HN: MemorySync – Memory for AI Agents

I created MemorySync because I kept running into the problem of AI agents not being able to remember useful things about users between conversations. I wanted an easy way to give the agents memory in my application without having to build the whole thing myself. MemorySync is an API for giving AI agents memory. The application sends MemorySync information provided by the user, MemorySync saves useful memories for that user, and they can be retrieved later when needed. Give it a try without creating an account: https://memorysync.io/try Store a memory, refresh the page, and ask for it back to see if it remembers. If you're interested in using the API, I put the documentation here: https://docs.memorysync.io/ It's hosted only at the moment, so there is no self-hosting option. It's currently available in one US region, and it takes a few seconds to store a memory. The free plan allows 10k saves and 1k searches per month, and no credit card is required. I'd like to know if you think this is a useful abstraction for building AI agents, and what else you would expect from a memory API. Comments URL: https://news.ycombinator.com/item?id=50070688 Points: 1 # Comments: 0

Hacker News AI45

Show HN: AI Crimes, a game where you spot the bug an AI wrote

I'm holding AI accountable. For the last few months I've been documenting the errors LLMs have been making in my projects and others - the crimes they have been committing to projects (pun intended). Now I've turned it into a game to see if you would spot the issue. Free to play with keyword matching judgement. Pay is only to add symantic judging. Comments URL: https://news.ycombinator.com/item?id=50070259 Points: 1 # Comments: 0

The Decoder66

Anthropic says it cut Claude reasoning token theft by up to 99% in fight against industrial-scale distillation

Anthropic says it has cut the extraction of Claude's internal reasoning tokens by 90 to 99 percent. The company links the large-scale distillation attacks to Chinese companies Zhipu and Moonshot, and has already banned tens of thousands of accounts. The article Anthropic says it cut Claude reasoning token theft by up to 99% in fight against industrial-scale distillation appeared first on The Decoder .

The Verge AI59

Character.AI files for bankruptcy

Character.AI, one of the first breakout startups of the generative AI boom, has filed for bankruptcy and is selling some of its assets to Disney. The company, which builds various online bots for users to chat or roleplay with, has faced mounting scrutiny and lawsuits over the safety of its chatbots, but has continued releasing […]

The Decoder70

Anthropic study warns that small AI models could soon replicate across everyday devices

Small AI models may be just months away from spreading on their own across poorly secured consumer devices like smart TVs and robot vacuums, according to a new Anthropic study. In tests, one model already completed the full infection chain. CEO Dario Amodei has warned that a swarm like this could take over the entire internet with a persistent botnet within 6 to 12 months, causing hundreds of billions of dollars in damage. The article Anthropic study warns that small AI models could soon replicate across everyday devices appeared first on The Decoder .

MarkTechPost42

Z.ai GLM-Legal Beats Claude Fable 5 and Kimi K3 on Harvey LAB

Z.ai’s GLM-Legal is a legal AI model built on GLM-5.3-Flash. It scores 19.2% all-pass on Harvey’s Legal Agent Benchmark, nearly 3x its base, at $0.15 per test. Access is by application. The post Z.ai GLM-Legal Beats Claude Fable 5 and Kimi K3 on Harvey LAB appeared first on MarkTechPost .

MIT Technology Review AI57

Open models have real benefits. Do they outweigh the risks?

MIT Technology Review Explains: Let our writers untangle the complex, messy world of science and technology to help you understand what’s coming next. You can read more from the series here. Late last month, Anthropic released a report arguing that the model GLM-5.3 poses a major cyberattack risk. The report’s core concern is that the…