16 Ways to Make a Small Language Model Think Bigger

<!-- SC_OFF --><div class="md"><p>Projects are <a href="https://github.com/snap-research/locomo/issues/31">still submitting new scores on LoCoMo as of March 2026.</a> but the

<blockquote> <p>📺 Prefer to watch? <a href="https://youtu.be/bj9ZYwoI7_k" rel="noopener noreferrer">90-second YouTube Short</a> · 💬 <a href="https://t.me/SoftwareEngineerBlog"

<p><a class="article-body-image-wrapper"

<p>57% of organizations estimate their data isn't AI-ready. General-purpose LLMs handle broad tasks well but hallucinate on specialized queries, miss domain jargon, and can't

<ul> <li>GitHub repository: <a href="https://github.com/gezilinll/agent-grove" rel="noopener noreferrer">https://github.com/gezilinll/agent-grove</a> </li> <li>Online

<p><strong>TL;DR:</strong> I built the same browser agent twice — once with 500 lines of Python, once with 7 lines of JSON. The second one took 5 minutes. The agent harness layer

<p><em>We stopped measuring retrieval quality by how many tokens we could fit into the prompt.</em></p> <p>When long-context models became available, many of us made the same

<p>Most "multimodal" AI products today are really a relay team. One model plans, then hands the job to an image model, a video model, a detector, or a robot policy. Reka's new