93 stories
I built a role-play game with LLMs and expected werewolves on spaceships and in abandoned castles. Some players had a different idea. What happened I have a little Werewolf text game with LLMs. With a caveat - there is a role-play.
Built for the TigerGraph Agentic GraphRAG Hackathon. Repo and dashboard linked at the end. RAG retrieves text. GraphRAG adds structure. Agentic GraphRAG lets a model plan its own investigation. Everyone assumes the third one is better — but by how much, and on which questions?
The Ghost in the Machine: My Robot Vacuum's Existential Crisis (and Ours) My robot vacuum, Bartholomew, has started avoiding the rug in the living room. Not all the time, just on Tuesdays.
AI phone agents went from obviously robotic to occasionally indistinguishable from a person in about two years. The reason is not one breakthrough. It is that three separate components got good at the same time, and the engineering problem of connecting them got solved well enough.
GPT-6.1 Sol dan Claude Sonnet 5.5 sama-sama berharga $2 per juta token input dan $10 per juta token output. Keduanya juga dirilis selisih satu hari: Sonnet 5.5 pada 28 September 2026, lalu GPT-6.1 Sol pada 29 September.
Untuk memanggil API GPT-6.1 Sol, kirim permintaan POST ke https://api.openai.com/v1/responses dengan "model": "gpt-6.1-sol" dan token Bearer Anda. Harga standar tetap $2 untuk input dan $10 untuk output per juta token, tetapi input yang di-cache turun dari $0,20 menjadi $0,10.
Để gọi API GPT-6.1 Sol, gửi yêu cầu POST đến https://api.openai.com/v1/responses với "model": "gpt-6.1-sol" và API key dưới dạng Bearer token. Giá niêm yết giữ nguyên ở mức 2 đô la đầu vào và 10 đô la đầu ra cho mỗi triệu token như GPT-6 Sol, nhưng đầu vào đã cache giảm từ 0,20 đô la xuống 0,10 đô…
Para chamar a API GPT-6.1 Sol, envie uma requisição POST para https://api.openai.com/v1/responses com "model": "gpt-6.1-sol" e sua chave como token Bearer. O preço permanece em US$ 2 de entrada e US$ 10 de saída por milhão de tokens, como no GPT-6 Sol.
GPT-6.1 Sol y Claude Sonnet 5.5 cuestan $2 por millón de tokens de entrada y $10 por millón de tokens de salida. Se lanzaron con un día de diferencia: Sonnet 5.5 el 28 de septiembre de 2026 y GPT-6.1 Sol el 29 de septiembre. Ningún proveedor los ha comparado directamente.
I Built a Sales Assistant That Actually Remembers Customers What if your sales assistant could write the perfect email… …but had no idea who the customer was? That bothered me while building AI sales assistants. Today, an LLM can write a convincing email in seconds. It can summarize a meeting.
What Happened When DealMind Could Recall Past Objections Building persistent deal memory with Hindsight changed how I thought about context, retrieval, and the boundary between application state and agent memory. The first version of DealMind could answer questions about a deal.
Only Gemini Failed My False-Premise Benchmark — 7 Models Tested The itch I kept noticing a specific failure mode: when a question embeds a false assumption, most models correct the user cleanly — but some play along and confabulate detailed answers that fit the wrong premise.
OpenAI DevDay 2026 ran on 29 September at Fort Mason in San Francisco. Sam Altman opened at 10:00 AM Pacific, with Romain Huet, Tejal Patwardhan and Holly Li following him on stage.
Every instrumentation layer is an interrogation. You add a trace, and the trace changes the testimony. When we wrap an agent's reasoning chain with logging, we are not passive observers. We are inserting variables into the system's decision surface.
I Built a Sales Assistant That Actually Remembers Customers What if your sales assistant could write the perfect email… …but had no idea who the customer was? That bothered me while building AI sales assistants. Today, an LLM can write a convincing email in seconds. It can summarize a meeting.
Sales conversations rarely happen in isolation. A customer might discuss pricing in one call, raise an objection in another, introduce a new stakeholder later, and finally ask for a specific next step several conversations after the first meeting. The problem is that these details are easy to lose.
The worst call my voice agent ever made went like this: "Hi Imran, Aisha from TableTap. Our billing app starts at just nine hundred ninety nine rupees a month." Imran runs a cloud kitchen.
Building Stateful AI Workflows: Moving Past Raw Logs with Long-Term Agent Memory If you've ever watched an LLM-powered assistant forget a critical workflow decision three turns after you made it, you already know the wall that stateless agent architectures hit.
Showing 90 of 93 stories
Load more storiesGet the top AI news and tools straight to your inbox every week.
Weekly · AI news from Dev.to AI
Join 15,000+ AI enthusiasts
