24 Aug 2026 · 15 articles
LangChain and Fireworks fine-tuned an open model to mine perceived error signals from production traces, matching frontier model performance at a fraction of the cost.
Summary published by LangChain Blog · 21 Aug 2026 · Read the original ↗
A few interesting numbers in this FT story gathered from "people with knowledge of the matter": Anthropic's "annualized revenue" for July is up to $65bn - it was $47bn in May, and I collected more historic numbers here . Anthropic expect Q3 to be profitable according to the same model they used to declare Q2 profitable. "It also told investors that it had 6,000 customers that spend $100,000…
Summary published by Simon Willison's Weblog · 23 Aug 2026 · Read the original ↗
Prior to Fable, it felt silly to waste too much time improving your coding harness or context strategies. A new model would arrive at the same price (or cheaper!) and paper over most of your problems. But then Fable landed. It was (and still is!) incredible . But the cost was so high and Opus was good enough (as was 5.6, K3, and even GLM) for most of the code we needed. So we…
Summary published by Simon Willison's Weblog · 23 Aug 2026 · Read the original ↗
Release: llm 0.33 My highlights from this release: Upgraded to the OpenAI Python library 3.x and switched the HTTP client dependency from httpx to httpx2 . #1608 , #1631 I shipped a quick 0.32.1 fix for this yesterday, but this is the more comprehensive fix. llm embed and llm embed-multi now accept --key . The Python EmbeddingModel.embed() , EmbeddingModel.embed_multi() , Collection.embed() and…
Summary published by Simon Willison's Weblog · 22 Aug 2026 · Read the original ↗
The key skill required to make productive use of coding agents is being able to confidently instruct them on how to make changes and then confidently verify that those changes have been applied in the correct way. Sometimes this involves reviewing every line of code they have written, but there are other ways to achieve that goal. Eyeballing every line of code has never been the most effective…
Summary published by Simon Willison's Weblog · 22 Aug 2026 · Read the original ↗
Release: llm 0.32.1 Fresh installs of LLM stopped working the other day because the OpenAI Python library dropped its usage of httpx , and it turned out LLM depended on that library but only installed it via a transitive openai dependency. This dot-release fixes that for the moment by pinning to openai<3 , and a soon-to-drop 0.33 release will switch from httpx to httpx2 . Tags: httpx , openai…
Summary published by Simon Willison's Weblog · 21 Aug 2026 · Read the original ↗
Release: llm-openrouter 0.7 Now that this plugin is compatible with LLM 0.32 it can display the reasoning traces for LLMs available through OpenRouter. Updated for compatibility with LLM 0.32 . Models now use OpenRouter's implementation of the Responses API . Three new server-side tools: Shell , WebFetch , and WebSearch . Enable these with options like -T WebSearch . Tags: llm , openrouter
Summary published by Simon Willison's Weblog · 21 Aug 2026 · Read the original ↗
A Google DeepMind engineer breaks full-stack development into five simple layers and explains how it affects everyday users.
Summary published by Google DeepMind · 21 Aug 2026 · Read the original ↗
Article URL: https://mathstodon.xyz/@maxpool/117128107757895678 Comments URL: https://news.ycombinator.com/item?id=49382041 Points: 189 # Comments: 209
Summary published by Hacker News - Newest: "AI" · 21 Aug 2026 · Read the original ↗
We ran 904 DeepSWE rollouts on GLM-5.3 and GPT-5.6 Sol. Sol leads pass@1 by 3.7 points; GLM-5.3 wins pass@4 at half the cost, and a GLM-first cascade hits 85.9%.
Summary published by Together.ai · 21 Aug 2026 · Read the original ↗
We ran 904 DeepSWE rollouts on GLM-5.3 and Claude Fable 5. A tie on pass@1, but GLM-5.3 wins pass@4 and costs 5.4x less: \$3.99 per rollout vs. \$21.63.
Summary published by Together.ai · 21 Aug 2026 · Read the original ↗
Promptwatch is part of the emerging "GEO" space, for Generative Engine Optimization - the chatbot version of SEO, where companies offer tools and consulting to help your site increase its presence in replies to prompts inside tools like ChatGPT. The Promptwatch product uses automation to track responses to prompts across end-user chat products like ChatGPT, Claude, and Gemini. They publish…
Summary published by Simon Willison's Weblog · 20 Aug 2026 · Read the original ↗
Preview Builds let teams test pull request branches in temporary, production-like LangSmith deployments before merging agent changes.
Summary published by LangChain Blog · 20 Aug 2026 · Read the original ↗
Hello everyone. I've been working on this experimental editor called Huzzah. I've been working almost exclusively with coding agents since January of this year, and over the past few months I began to feel utterly exhausted by them. They're great, but I'm finding it more and more tedious to write full sentences for every change I want. Not only that, but it seems there's a complexity limit for…
Summary published by Hacker News - Newest: "AI" · 20 Aug 2026 · Read the original ↗
Research: A shot-scraper-style JSON API on Bun 1.4's new Bun.WebView Today saw the long awaited release of Bun 1.4 , the first stable version since the infamous Rust rewrite a few months ago . Interestingly, the Rust rewrite was downplayed in the release notes, which introduced a bewildering array of new features and claimed 2,900 additional bug fixes: Bun 1.4 adds +1,517 tests from the Node.js…
Summary published by Simon Willison's Weblog · 20 Aug 2026 · Read the original ↗