I genuinely think we built the best search engine for official economic data. Been working on this for 6 months. We spent ~$100k in tokens to structure economic data and make it easier to search. It's answers economic data really well. From "What has been the actual impact of AI on software engineering jobs in the last 2 years?" to "Why did egg prices increase so much more than chicken prices in the last 5 years?" Would love feedback (the more blunt the better). We have a generous free tier for the next week!

We abandoned training our own models at Defog in 2024 (despite 2M huggingface downloads) after o1 was released Our reasoning at the time - frontier models would get better and cheaper. It was just easier to use them via an API, and see gains automatically, rather than painfully handcraft our own Fully realizing the risks of that decision today. Going to spend at least a third of my time on fine-tuning frontier open-source models moving forward. Can't build a business on shifting sands, gotta own your model weights.

Welp. Time to start getting better at finetuning and relying on open weights again

brain feels fried. trying to fablemax while it's still subsidized on the max plan made more work progress in 2 days than i did all of last month. but constant context switching and "brain-must-go-brr" is exhausting

friends don’t let friends use vector search without guardrails

Today, we’re re-launching FactIQ. Six months ago, we launched a search and visualization engine for economic data. You could ask for a dataset, find the right series, and turn it into a chart. But over the last few months, the role of agents has changed. They are no longer just useful for saving a few minutes on repetitive work. They now act like a tireless second pair of eyes. Digging through data, testing competing explanations, and surfacing evidence you may not have looked out for. That opened up a much bigger opportunity for FactIQ. Macro analysts don’t just need another way to make charts. They need to answer the hardest and most important question in research: what’s actually happening? Answering that means looking beyond the obvious narrative. Beyond the single indicator everyone is watching. Beyond the chart that confirms what you already believed. The new FactIQ turns a macro question into an investigation. It breaks the question into the explanations that could be true, searches across official data, global institutions, government releases, news, and trusted industry sources, and tests which explanations are actually supported by the evidence. The goal is simple: give every macro analyst the capabilities of an institutional research desk. Use FactIQ to write macro notes, brief clients, support investment decisions, or pressure-test your view before publishing it. Try it today at factiq.com. We would love to know what you think.

Jfc Asian public markets are retarded when it comes to AI Zhipu (GLM maker) is trading at a US$92B valuation, with ttm sales of ~US$100M (920x multiple) Wild to see a public co trading on Series A metrics The bubble is already here. It's just not evenly distributed.

Sadness. Gemini 3.5 Flash is as haunted as 3 Flash I _really_ wanted it to work. But it's totally broken in non-Google harnesses Way slower (and worse) than GPT-5.5/Opus at tool-chaining - despite the high output tok/s

for frontend agents, don't go from specs to code directly instead, to specs -> gpt-image-2 -> frontend code beats any coding agent out there. phenomenal tip from @reach_vb!

Early GPT-5.5 impressions - finally an OAI model that matches Claude at tool calls Until yesterday, Opus/Sonnet were the only reliable options if you wanted to build a fast, long-running agent. GPT-5.4 was good, but thought too much, and was super slow. It also polluted the context with too many thinking tokens and so had degraded performance at long-running tasks. Gemini models are... just weird at tool calling - they often get stuck in infinite loops. GPT-5.5 costs slightly less than Opus across the tool calling loop, is just as fast, and just as good. I like its personality more - much less hedging (specially for things like financial analysis) and more to the point. It's also much more broadly useful. Codex with GPT-5.4 was pretty good at code, but Opus was just better for general tasks. GPT-5.5 feels super competent across the board. Really excited for this release. Makes the LLMs for AI-agent market competitive again!

The last time I dealt with model regressions this bad was in the GPT-4 era. Sonnet is borderline unusable today. Anthropic will lose so much market share if they don't secure more compute, and fast.

Something _very_ weird is up with Sonnet 4.6 rn. Tool calls are totally broken 🫠

Welp, it's starting to happen. Under-discussed from the JOLTS report yesterday

Sigh does everyone saying "it will be expensive to maintain AI generated code" not know about --dangerously-skip-permissions Give Claude Code / Codex a sandbox, let it poll for updates/canges, auto push and review PRs, set up CI/CD. Automated, better-than-human maintenance 🤷🏽‍♂️

sigh. i hope anthropic changes their auth provider soon (or better yet - use a homebrewed solution). their current one seems very broken