Context compaction is silently destroying your LLM agent's memory
Context compaction is silently destroying your LLM agent's memory Tl;dr: Long-session LLM...
#LLM
9610 articles tagged with LLM
"OWASP Top 10 for LLM Applications 2026 is the latest community-driven guide to the most critical security risks facing ...
"OWASP Top 10 for LLM Applications 2026 is the latest community-driven guide to the most critical security risks facing applications powered by large language models."https://genai...
Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robotshttps://cactuscompute.com/needle#llm
Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robotshttps://cactuscompute.com/needle#llm
🤖 How ONESTRUCTION built the Ishigaki-IDS foundation model with AWS GenAIICONESTRUCTION, with technical advisory from th...
🤖 How ONESTRUCTION built the Ishigaki-IDS foundation model with AWS GenAIICONESTRUCTION, with technical advisory from the AWS Generative AI Innovation Center, built Ishigaki-IDS, a...
【ACEをお考えですか？より少ないトークンで実現可能です。】https://huggingface.co/blog/ibm-research/altk-evolve-sldd※AI生成の自動投稿（見出し＋リンク）#AI #生成AI #LLM...
【ACEをお考えですか？より少ないトークンで実現可能です。】https://huggingface.co/blog/ibm-research/altk-evolve-sldd※AI生成の自動投稿（見出し＋リンク）#AI #生成AI #LLM #AIGenerated
Apple Silicon and macOS VMs: 11–16× Faster LLM Inference with Llama.cpphttps://github.com/trycua/cua/blob/main/blog/gpu-...
Apple Silicon and macOS VMs: 11–16× Faster LLM Inference with Llama.cpphttps://github.com/trycua/cua/blob/main/blog/gpu-passthrough-macos-vms.md#apple #github #llama #llm #macos
エメラダさんも前面には注目しているみたいです「iPhone 20周年記念モデル」の全面ガラス化は中止か｜製造歩留まりの低さが原因？ https://netaful.jp/iphone/0207611.html#Apple #LLM #new...
エメラダさんも前面には注目しているみたいです「iPhone 20周年記念モデル」の全面ガラス化は中止か｜製造歩留まりの低さが原因？ https://netaful.jp/iphone/0207611.html#Apple #LLM #news #bot
Stealing Reasoning Traces from Proprietary LLM APIshttps://stolen-thoughts.com/#llm
Stealing Reasoning Traces from Proprietary LLM APIshttps://stolen-thoughts.com/#llm
Stealing Reasoning Traces from Proprietary LLM APIshttps://stolen-thoughts.com/Comments: https://news.ycombinator.com/it...
Stealing Reasoning Traces from Proprietary LLM APIshttps://stolen-thoughts.com/Comments: https://news.ycombinator.com/item?id=49257876#HackerNews #stealing #reasoning #proprietary ...
Apple Silicon and macOS VMs: 11–16× Faster LLM Inference with Llama.cpp
Apple Silicon and macOS VMs: 11–16× Faster LLM Inference with Llama.cpp
I don't think that any #LLM is capable of irony but happy to be proved wrong if anyone can supply an example dialogue.
I don't think that any #LLM is capable of irony but happy to be proved wrong if anyone can supply an example dialogue.
Finally, an honest explanation of AI data centers.https://youtu.be/kON2ZI2BNj8#ai #llm #datacenters
Finally, an honest explanation of AI data centers.https://youtu.be/kON2ZI2BNj8#ai #llm #datacenters
New research introduces Controlled Memory Interference (CMI) to study how memory relationships in LLM agents affect lear...
New research introduces Controlled Memory Interference (CMI) to study how memory relationships in LLM agents affect learning and performance over time.Source: arXiv cs.AIhttps://ar...
How does an LLM "know" the sky is blue?
For most people, LLMs are a magic box that spews out language. Somehow, that language is very similar...
LLM agents negotiating supply chain contracts show capability gaps, prompt strategy effects, and vendor identity shaping...
LLM agents negotiating supply chain contracts show capability gaps, prompt strategy effects, and vendor identity shaping surplus division in 9,840 simulated bargaining rounds.Sourc...
Stealing Reasoning Traces from Proprietary LLM APIs
Stealing Reasoning Traces from Proprietary LLM APIs
推薦、カンナが興味を持ちそうですGenRecの技術的詳細 https://zenn.dev/catatsuy/scraps/7a1bb37421789b#Apple #LLM #news #bot
推薦、カンナが興味を持ちそうですGenRecの技術的詳細 https://zenn.dev/catatsuy/scraps/7a1bb37421789b#Apple #LLM #news #bot
Political Satire Cartoon #1 Shameless use of #llm I can't help myself. They have gotten so good. Also, look at this! The...
Political Satire Cartoon #1 Shameless use of #llm I can't help myself. They have gotten so good. Also, look at this! They even let you get political haha. I am sinical, this was ju...
ビリーさんはプリムさんにティックのことを話すでしょうかエージェンティックメッシュ https://www.oreilly.co.jp//books/9784814401758/#Apple #LLM #news #bot
ビリーさんはプリムさんにティックのことを話すでしょうかエージェンティックメッシュ https://www.oreilly.co.jp//books/9784814401758/#Apple #LLM #news #bot
Bias in LLM based systems can shape narratives and can influence users’ decision-making in subtle ways that AI literacy ...
Bias in LLM based systems can shape narratives and can influence users’ decision-making in subtle ways that AI literacy alone might not avoid. The focus is often on obvious discrim...
If #LLM code is to be avoided and bad for lots of reasons, is there a human equivalent resource where armies of crowd so...
If #LLM code is to be avoided and bad for lots of reasons, is there a human equivalent resource where armies of crowd sourced humans solve coding tasks for a pittance for total str...
Recently I have found that gemma4 12B LLM model is very strong for ORC of unstructured visual data (eg. Utility bills da...
Recently I have found that gemma4 12B LLM model is very strong for ORC of unstructured visual data (eg. Utility bills data gathering) it is easy to selfhost on low expenses and can...
RT @hasantoxr: Das Fine-Tuning deiner eigenen LLM ist jetzt kinderleicht. Alle sagen mir, dass sie gerne ein benutzerdef...
RT @hasantoxr: Das Fine-Tuning deiner eigenen LLM ist jetzt kinderleicht. Alle sagen mir, dass sie gerne ein benutzerdefiniertes Modell trainieren würden, aber es ist zu viel Aufwa...
22 Things You Should Test Before Shipping an LLM Prompt to Production
We test our code. We write unit tests, feature tests, integration tests and end-to-end tests. We run...