DealForge autonomously sources, scores, and writes investment memos on venture deals. Stop manually hunting.

1,180+ deals tracked  ·  22 AI investment memos  ·  Updated daily

← Back to leaderboard

Control your X/Twitter feed using a small on

Show HN: Control your X/Twitter feed using a small on-device LLM

43 AI Score
Show_hn other Added Apr 9, 2026

Details

Sector
other
Total Funding
$0
Last Round
$0

About

We built a Chrome extension and iOS app that filters Twitter&#x27;s feed using Qwen3.5-4B for contextual matching. You describe what you don&#x27;t want in plain language—it removes posts that match semantically, not by keyword.<p>What surprised us was that because Twitter&#x27;s ranking algorithm adapts based on what you engage with, consistent filtering starts reshaping the recommendations over time. You&#x27;re implicitly signaling preferences to the algorithm. For some of us it &quot;healed&quot; our feed.<p>Currently running inference from our own servers with an experimental on-device option, and we&#x27;re working on fully on-device execution to remove that dependency. Latency is acceptable on most hardware but not great on older machines. No data collection; everything except the model call runs locally.<p>It doesn&#x27;t work perfectly (figurative language trips it up) but it&#x27;s meaningfully better than muting keywords and we use it ourselves every day.<p>Also promising how local &#x2F; open models can now start giving us more control over the algorithmic agents in our lives, because capability density is improving.

AI Score Reasoning

The project demonstrates a clever application of small language models (SLMs) to solve a pervasive user experience issue on social media, but it faces extreme platform risk as it relies on X/Twitter's UI and API stability. While the technical approach to on-device inference is forward-thinking, the lack of a clear moat or monetization strategy makes it more of a high-utility tool than a venture-scale business at this stage.

Source

Show_hn — View original →