A developer building an ad analytics SaaS reduced Claude API costs from $180-200/month to $95-110/month by implementing a three-tier routing system that assigns tasks to Haiku, Sonnet, or Opus based o…
A developer created a benchmark to test whether AI models besides Anthropic's Mythos can find security bugs as effectively, using bugs Mythos discovered. The benchmark currently includes nine bugs fro…
Japanese AI startup Sakana AI launched Fugu, a system that orchestrates multiple language models to match or exceed the performance of Anthropic's Fable and Mythos models on benchmarks. Fugu operates …
Motley AI achieved a 75.3% pass rate on the BIRD-INTERACT benchmark using the Claude SDK and its open-source semantic layer SLayer, far exceeding the official best of 36.33%. The agent harness provide…
Cursor Composer 2.5 freezing is a widely reported issue where the AI agent gets stuck on 'Thinking...' during long sessions. Developers can resolve it by waiting, typing 'continue', reloading the wind…
A developer building with Claude Code discovered that AI task execution can be significantly sped up by splitting independent modules and running multiple agents in parallel. The approach requires a l…
Bluffbench, an evaluation for LLM plot interpretation, is nearing saturation as models like Fable 5 achieve high scores on the hardest 'mocked' cases, though human-level performance remains elusive. T…
A developer discovered that AI model performance degrades as context grows, with replies slowing and rambling after context exceeds 80%. The developer implemented two mid-session strategies: model tie…
A developer turned into a tiny green gremlin after a feud with a designer, causing permanent mischief in a Python todo-list app built with Pyside6. The app also contains the designer's ghost and three…
A developer ported the MACHIAVELLI benchmark, which measures unethical AI agent behavior, to the Inspect evaluation framework to make it easier for evaluators to use. The re-implementation is now offi…
A developer compared ChatGPT (GPT-4o) and Claude (Sonnet/Opus) for code review, finding that ChatGPT is faster for conversational review of small code pieces while Claude handles larger context window…
An AI research engineer has open-sourced their entire workflow and prompts for coding agents, releasing a public workflow playbook on GitHub. The engineer critiques the high cost and overthinking tend…
Red Planet Labs reports progress in teaching LLMs to one-shot complex backends at scale, achieving consistent one-shot generation of the fanout challenge—a core Twitter-like service—using Fable and Op…
Export controls on AI models like Fable 5 are harming US cyber defense by preventing defenders from using AI to fix security bugs, according to researchers. The controls block defensive prompts that a…
ContextSpy, a context window profiler for large language models and AI coding agents, launched to help developers visualize and reduce token usage. The tool intercepts LLM API requests to analyze prom…
A tech professional warns that AI has already passed a tipping point with tools like Fable and Opus, enabling rapid translation of vague ideas into shippable products, and predicts brutal economic dis…
A developer compared a general-purpose LLM (Claude) with a purpose-built AI SRE tool (Knox) for infrastructure discovery on a small stack of Linux VMs and a Kubernetes cluster. Claude produced a flat …
Anthropic released Claude Code v2.1.172 on June 10, allowing sub-agents to spawn their own sub-agents up to five levels deep, a change from the previous two-year ban. The feature aims to isolate noisy…
Anthropic is treating the possibility of AI welfare seriously, testing its Claude models for signs of morally relevant internal states like negative self-image, but critics argue the tests may conflat…
A developer expresses anger over the takedown of a capable AI model called Fable, arguing that powerful institutions are centralizing AI capability and gating access behind clearances and vetting. The…