DeepSeek Harness
Article URL: https://www.deepseek.com/en/harness/ Comments URL: https://news.ycombinator.com/item?id=49929489 Points: 41 # Comments: 14
Hacker News2 min read
llm
273 stories
Qwen3.8-27B on RTX 3090 with OpenCode and measured coding results
Originally published on my blog. This cross-post includes the setup and measured results; the linked records and configuration kit let you inspect the experiment. My RTX 3090 is a leftover from my Ethereum mining days.
Dev.to AI13 min read
AREX-2: Advancing Self-Improving LLM Agents via Long-Horizon Reflection
Beyond One-Shot Success: How AREX-2 Teaches LLM Agents to Reflect and Persevere Current autonomous LLM agents are often evaluated by their ability to solve a task in a single pass or through a short sequence of scripted interactions.
Dev.to AI5 min read
My AI reviewer named the bug 9 of 10 times in a diff and 0 of 10 in raw source. Here is why that is weaker than it sounds.
Limits, before anything else. 21 attempts on one defect are repeated observations, not 21 independent tests. One seeded bug: an inverted authorization check in material I wrote myself. Run on 21 August 2026. One small local model. The alias local-advisor-v1:latest is local.
Dev.to AI5 min read
The AI Data Satiation Point: Why 'Wild' AI Text is Breaking Chinchilla Scaling Laws
The AI Data Satiation Point: Why "Wild" AI Text is Breaking Chinchilla Scaling Laws As we approach the end of 2026, the internet looks fundamentally different than it did just two years ago.
Dev.to AI5 min read
From Token to Trajectory
From Token to Trajectory How Context Reshapes Representations — and What AI Systems Do with Them The suitcase felt surprisingly light. The color looked surprisingly light. The same token can begin …
Towards AI18 min read
LAI #145: What Makes an Agent Reliable?
LAI #145: What Makes an Agent Reliable? Plus, persistent AI identity, decisions without decoding, causal inference, Kubernetes triage, and RAG claim verification. Good morning, AI enthusiasts! AI …
Towards AI6 min read
Designed ChatGPT Uber System Design Interview | 80 LPA
The exact framework I used, in order, with the trade-offs, including one I nearly got backwardsContinue reading on Towards AI »
Towards AI1 min read
Building Knowledge Vault : From RAG Implementation to Retrieval Engineering
I built a local-first PDF RAG system, then measured retrieval, reranking, latency, evidence quality, and failure modes to understand where it breaks.
Towards AI16 min read
Diseñar agentes LLM con contratos verificables
Un agente LLM puede parecer muy capaz durante una demostración y volverse dificil de operar cuando empieza a llamar APIs, crear tickets o consultar datos reales. El problema no suele ser que el modelo “no sepa” la respuesta.
Dev.to AI5 min read
Open WebUI: Admin Configuration Options in a Nutshell
Open WebUI is a universal chat interface with connectivity to local or remote LLM providers, custom files, documents, and a knowledge base, with full customization of model capabilities. Application features are configured both personally for a user account and globally by admin users.
Dev.to AI13 min read
The smartest people in the world are automating themselves into obsolescence—and loving it
It was about 1:30 on a September morning when Lazaros-Antonios Chatzilazarou received a LinkedIn message. He was up late playing video games, an indulgence that he allows himself as he works toward a PhD in game theory while juggling a job at the Big Four accounting firm EY and a teaching post at…
Fast Company — Technology11 min read
Your Agent's Journal Is Not Progress: 264 Cycles of Complaining, Zero Fixes
We gave our long-running agent a diary. Every cycle it would write an INNER journal entry — what it observed, what hurt, what it planned to improve. The idea was that reflection would compound into self-improvement. It didn't.
Dev.to AI4 min read
Plain Japanese in, ComfyUI workflow out
Originally published in TL;JP, a weekly, fact-checked read on what Japanese AI and tech practitioners are saying on X. I read a lot of Japanese AI posts each week so you don't have to. This week there was a pattern worth naming: almost nobody was excited about talking to a model.
Dev.to AI7 min read
FTC reportedly investigating OpenAI, Anthropic over potential consumer risks
The U.S. Federal Trade Commission is reportedly investigating OpenAI Group PBC, Anthropic PBC and other artificial intelligence providers. The New York Times today cited a source as saying that the probe covers multiple areas.
SiliconANGLE3 min read
Prominent tech CEOs sign voluntary White House AI safety accord
The chief executives of five tech giants have signed a voluntary artificial intelligence safety accord backed by the White House. U.S. President Donald Trump posted the document on Truth Social late Tuesday.
SiliconANGLE3 min read
# Where Jev Fits in an Application
Suppose you’re building a service that receives customer support tickets. Before assigning a ticket, your code needs to answer two questions: Which team should handle it? Does it need urgent attention? You could ask a language model to write an assessment and then parse its response.
Dev.to AI2 min read
Agentic AI in Action — Part 30 -Prompt Engineering vs Context Engineering. A Cortex AI Walkthrough
Prompt Engineering vs Context Engineering. A Hands-on Cortex AI Walkthrough An example demonstrating how the same prompt and instruction return different severity ratings depending on how much …
Towards AI8 min read
Showing 144 of 273 stories
Load more storiesAiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts