Top all-time · #12324
Continue Blog
Company blog · blog.continue.devaiprogramming
Continue Blog is the company blog at blog.continue.dev, writing about ai and programming. Since 2023, 6 different Hacker News readers have linked it 10 times. It is still writing: the last post was on 2026-03-06, and you can follow it by feed.
Too few sampled comments (6) to say how often HN recommends it.?
Why HN links it
Linked for posts on the Instinct open completion model, custom AI code assistants, intervention rates in coding agents, and the move toward source-controlled checks in CI. Comments cite them without judging the writing.
Summarised by Claude from a sample of 6 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
News, updates, and insights from the Continue team.
Most-linked posts?
- /its-time-to-collect-data-on-how-you-build-software/2 people · 2 mentions · first linked 2024-02-17
What Hacker News says?
Have you tried continue.dev's new open completion model [1]? How does it compare to llama.vscode FIM with qwen? [1] https://blog.continue.dev/instinct/
Comment linking /instinct/
on “Ask HN: Who uses open LLMs and coding assistants locally? Share setup and laptop”Submitted Continue, the open-source Copilot alternative, has raised $2.1m as a story · 7 points
HN discussion> Copilot is encouraging us to block users unnecessarily, by suggesting obviously flawed code, which is wrong on every level: wrong ethically, wrong legally, and the wrong way to build software. I share many of the same worries as the author. This is why I think teams need to build and run their own Copilot-like systems, so that they can guide the suggestions they receive. Each developer and team has their own way o…
Comment linking /its-time-to-collect-data-on-how-you-build-software/
on “I worry our Copilot is leaving some passengers behind”Submitted Instant Apply as a story · 3 points
HN discussionI hear this often (I had the same gut reaction before thinking below the surface) and will share why I think that our bet is perfectly aligned with the Bitter Lesson being true 1. The Bitter Lesson extends to test-time compute (some call this the "Bitter-er Lesson" https://yellow-apartment-148.notion.site/AI-Search-The-Bitte... ), and we've bet that agentic LLMs will become a major transformation in how software is…
Comment linking /its-time-to-collect-data-on-how-you-build-software/
on “Launch HN: Continue (YC S23) – Create custom AI code assistants”Submitted An open source AI code assistant inside your editor as a story · 2 points
HN discussionhttps://blog.continue.dev/intervention-rates-are-the-new-bui... For example, error type distribution or intervention rates. This can tell me how efficient I am when using Claude. But currently, the error type is a bit too broad, and I haven’t discovered much yet.
Comment linking /intervention-rates-are-the-new-build-times/
on “Sniffly – Claude Code Analytics Dashboard”Submitted An introduction to code LLM benchmarks for software engineers as a story · 1 points
HN discussionThat's us! I figure others will wonder the same, so we wrote about what exactly we're doing here: https://blog.continue.dev/from-extension-to-mission-control tl;dr - a _lot_ of people still use the VS Code extension and so we're still putting energy toward keeping it polished (this becomes easier with checks : )) - our checks product is powered by an open-source CLI (we think this is important), which we recommend f…
Comment linking /from-extension-to-mission-control
on “Show HN: Continue – Source-controlled AI checks, enforceable in CI”You'll get our GPT-4 free trial for a while, but then after that you'll also have the option to use a local model, which would be free (though of course their quality doesn't quite yet match GPT-4) Currently, we want our product to be free for individuals. But there are many benefits to running a hosted Continue Server for an entire team, and we plan to monetize in this "multiplayer" fashion. One example of the impo…
Comment linking /how-we-made-continue-ide-agnostic
on “Show HN: Continue – open-source coding autopilot, now in JetBrains”