GPT-4-powered web searches for developers
Hi HN, Today we’re launching GPT-4 answers on Phind.com, a developer-focused search engine that uses generative AI to browse the web and answer technical questions, complete with code examples and detailed explanations. Unlike vanilla GPT-4, Phind feeds in relevant websites and technical documentation, reducing the model’s hallucination and keeping it up-to-date. To use it, simply enable the “Expert” toggle before doing a search. GPT-4 is making a night-and-day difference in terms of answer quality. For a question like “How can I RLHF a LLaMa model”, Phind in Expert mode delivers a…
In plain words
Phind is a developer-focused search engine that uses GPT-4 to answer technical questions by browsing the web and referencing relevant documentation. Users can enable Expert mode to receive detailed answers complete with code examples, citations, and step-by-step explanations. By grounding GPT-4 with actual websites and technical sources, Phind reduces hallucinations and keeps information current, particularly useful for complex programming tasks.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN, Today we’re launching GPT-4 answers on Phind.com, a developer-focused search engine that uses generative AI to browse the web and answer technical questions, complete with code examples and detailed explanations. Unlike vanilla GPT-4, Phind feeds in relevant websites and technical documentation, reducing the model’s hallucination and keeping it up-to-date. To use it, simply enable the “Expert” toggle before doing a search. GPT-4 is making a night-and-day difference in terms of answer quality. For a question like “How can I RLHF a LLaMa model”, Phind in Expert mode delivers a step-by-step guide complete with citations (https://phind.com/search?cache=0fecf96b-0ac9-4b65-893d-8ea57...) while Phind in default mode meanders a bit and answers the question very generally (https://phind.com/search?cache=dd1fe16f-b101-4cc8-8089-ac56d...). GPT-4 is significantly more concise and “systematic” in its answers than our default model. It generates step-by-step instructions over 90% of the time, while our default model does not. We’re particularly focused on ML developers, as Phind can answer questions about many recent ML libraries, papers, and technologies that ChatGPT simply cannot. Even with ChatGPT’s alpha browsing mode, Phind answers technical questions faster and in more detail. For example, Phind running on “Expert” GPT-4 mode can concisely and correctly tell you how to run an Alpaca model using llama.cpp: (https://phind.com/search?cache=0132c27e-c876-4f87-a0e1-cc48f...). In contrast, ChatGPT-4 hallucinates and writes a make function for a fictional llama.cpp. We still have a long way to go and would love to hear your feedback.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
