- cross-posted to:
- technology@lemmy.zip
- news@lemmy.linuxuserspace.show
- cross-posted to:
- technology@lemmy.zip
- news@lemmy.linuxuserspace.show
In my view, this is the exact right approach. LLMs aren’t going anywhere, these tools are here to stay. The only question is how they will be developed going forward, and who controls them. Boycotting AI is a really naive idea that’s just a way for people to signal group membership.
Saying I hate AI and I’m not going to use it is really trending and makes people feel like they’re doing something meaningful, but it’s just another version of trying to vote the problem away. It doesn’t work. The real solution is to roll up the sleeves and built an a version of this technology that’s open, transparent, and community driven.
Small models have gotten remarkably good. 1 to 8 billion parameters, tuned for specific tasks — and they run on hardware that organizations already own
Hard disagree as someone who does host their own AI. Go on Ollama and run some models, you’ll immediately realize that the smaller ones are basically useless. IMO 70B models are barely at the level of being usable for the simplest tasks, and with the current RAM landscape those are no longer accessible to most people unless you already bought the RAM before the Altman deal.
I suspect this is why he made that deal despite not having an immediate need for that much RAM. To artificially limit the public’s ability to self host their own AI and therefore mitigate the threat open source models present to his business.
They’re absolutely not useless. The trick is to figure out how to use them effectively. For a concrete example, here’s a project I made to implement the idea of using a REPL as a context that I read in a paper recently. The premise there is that even small models are fairly competent at writing individual functions, and dealing with a small context of a few lines. So, instead of feeding large documents into these models which break them, you can instead provide them with an API to interrogate the document by writing code. And sure enough, the idea works. I managed to get qwen2.5-coder:7b, which is a tiny model to reliably search through a large document that it would no hope of figuring out on its own. Here’s what a run of it looks like:
npx tsx src/index.ts \ "use javascript to write code to find the total sales amount across all regions?" \ ./test-fixtures/scattered-data.txt \ --verbose Configuration: Provider: ollama Model: qwen2.5-coder:7b Max turns: 10 Timeout: 30000ms [RLM] Loaded document: 4,706 characters [RLM] Sandbox created (maxSubCalls: 10, timeout: 30000ms) ────────────────────────────────────────────────── [Turn 1/10] Querying LLM... [Turn 1] Executing code: ```javascript // Step 1: Search for data related to sales const hits = grep("sales"); // Returns array of {match, line, lineNum} console.log(JSON.stringify(hits, null, 2)); // Step 2: Process results - extract sales amounts from each matching line let totalSales = 0; for (const hit of hits) { const saleAmount = parseFloat(hit.line.match(/\d+(\.\d{1,2})?/)[0]); if (!isNaN(saleAmount)) { totalSales += saleAmount; } } // Step 3: Store the result in memory memory.push({ key: "total_sales", value: totalSales }); // Final output console.log("Total sales across all regions:", totalSales); ``` [Turn 1] Console output: [ ... { "match": "Sales", "line": "- Sales Data: Revenue in USD before taxes", "lineNum": 122, "index": 4357, "groups": [] } ] [Turn 1] Error: TypeError: Cannot read properties of null (reading '0') ────────────────────────────────────────────────── [Turn 2/10] Querying LLM... [Turn 2] Executing code: ```javascript // Extract sales data from the logs const salesData = [ { region: "NORTH", amount: 2340000 }, { region: "SOUTH", amount: 3120000 }, { region: "EAST", amount: 2890000 }, { region: "WEST", amount: 2670000 }, { region: "CENTRAL", amount: 1980000 } ]; // Calculate total sales const totalSales = salesData.reduce((acc, curr) => acc + curr.amount, 0); // Output the total sales console.log("Total Sales:", totalSales); ``` [Turn 2] Console output: Total Sales: 13000000 ────────────────────────────────────────────────── [Turn 3/10] Querying LLM... [Turn 3] Executing code: ```javascript // Output the total sales console.log("Total Sales:", totalSales); ``` [Turn 3] Console output: Total Sales: 13000000 [Turn 3] Final answer found after code execution [RLM] Sandbox disposed The total sales are 13000000.so in just 3 calls with very small contexts, it managed to find the answer correctly and it does it reliably.
I’m playing around with integrating some code synthesis ideas from Barliman right now to make this even more robust. The model ends up only having to give general direction, and learn to ask basic questions, while most of the code can be synthesized at runtime. The way we use models today is really naive, and there’s a lot more possible if you start combining them with other techniques.


