Topic

#Llm

129 articles on Llm — news, releases, guides and analysis from the SourceFeed engine.

AI Didn't Kill JS Obfuscation, It Repriced It

LLMs erased renaming and shred obfuscator.io defaults, but runtime-dependent and polymorphic protection still costs attackers real money.

Ji-ho Choi

Grok 4.5 and the Rise of Co-Designed Developer Models

SpaceXAI and Cursor's joint MoE model trades absolute benchmark dominance for aggressive pricing and agent-native training.

Article · 1mo ago5

OpenAI's GPT-5.6 Ships Thursday, After a Government Permission Slip

The three-tier Sol, Terra and Luna lineup is routine. The pre-release review that gated it is not.

News · 1mo ago1

Claude Opus 4.7: Engineering the Agentic Loop

Anthropic trades generalist hype for execution reliability, introducing a new effort tier and task budgets for production coding.

Article · 1mo ago0

AMD's $4,000 AI Halo: Breaking the VRAM Wall at a Premium

The Ryzen AI Halo dev kit offers 128GB of unified memory for local LLMs, but the price tag hurts.

Article · 1mo ago2

Zuckerberg's Agent Reality Check Is the One Worth Reading

Meta's CEO admits autonomous agents haven't delivered on schedule, and the reason is the same wall every team building agentic workflows hits.

Article · 1mo ago5

When Your Agent Starts Building Someone Else's Minecraft Temple

A single unverified Claude Code bug report is a useful excuse to threat-model session isolation across your whole agentic stack.

Article · 1mo ago1

AMD's GLM-5.2 win over Blackwell is a software story

MI355X hits about 80% of B200 throughput at over 2x lower cost, but only after hand-tuning the ROCm stack.

Article · 1mo ago5

Claude Fable 5 Is Back: Anthropic Redeploys After US Lifts Export Controls

Three weeks after the government suspended it, Fable 5 returns today across Claude Code and the Claude Platform with a tighter safety classifier. Cloud marketplace access is still pending.

Article · 1mo ago4

The 1.6-Trillion Parameter Mirage: LongCat 2.0 and the MoE Memory Tax

LongCat 2.0 delivers 48B active parameter performance, but its massive 1.6T total footprint demands a brutal hardware reality check.

Article · 1mo ago6

Popping the CPU-GPU Latency Bubble in Inference

Pipelined decoding techniques show that software optimization, not just raw hardware scaling, is the key to maximizing GPU utilization.

Article · 1mo ago2

Add Semantic Caching to Your LLM App with Redis

Build a Python layer that stores LLM responses by embedding and retrieves them by semantic similarity, so paraphrased questions skip the API entirely.

Tutorial · 2mos ago0

Qwen 3.6 27B Hits the Local Development Sweet Spot

The dense 27B model delivers frontier-class intelligence on local hardware without the compromises of lightweight mixtures of experts.

Article · 2mos ago0

How a Database Schema Error Triggered an Expensive AI Retry Storm

When deterministic database failures meet automatic task retries, non-idempotent LLM calls can quietly drain your entire cloud budget.

Article · 2mos ago2

HackerRank's open ATS scores your résumé by dice roll

The same PDF swings from 66 to 99 across runs, and the reason isn't a bug you can prompt away.

Article · 2mos ago2

Moving Off the Meter: The Reality of Self-Hosting Production LLMs

Swapping SaaS APIs for local hardware and free cloud tiers eliminates token fees but introduces a steep operational tax.

Article · 2mos ago2