Viewing profile — veselin

Here, it appears they compare a single prompt "find IDOR", against a multi-agent system. However, one can also start far more sophisticated skills that spin up subagents and mostly…

The more I think on the problem, the more I believe this will be solved with US interventions. And the interventions will increase inflation by a lot, so prices will not go down. T…

Claude code itself spins a lot of its subagents with Haiku. The model has low hallucination rate, so it is great for exploration tasks. I guess this is what the best purpose of thi…

I would argue that with AI, this becomes less of an issue. Connect N services, deploy to bare metal. Granted, AI is an additional cost now local or remote. But so is the MacBook pe…

Exactly our experience too. Effectively we catch these and on these status codes, we send to OpenAI. Retrying the same query in Gemini has high chance to give kind-of the same stat…

I think this is a promise, probably also for spec driven development. You write the spec, the whole thing can be reimplemented in rust tomorrow. Make small modules or libraries. On…

This is an experiment that, although not to this extreme, was tested by OpenAI. Their responses API allow you to control verbosity: https://developers.openai.com/api/reference/reso…

I guess we will have a lot more benefits if we can get this to work on something like llama.cpp - since it really has a lot of kernels for different quantizations, a lot of home us…

I think they put two things: * Likely they will seek regulation that would ban some models. Not sure this can work, but they will certainly try. * Likely they will not release some…

I am actually going to complain about this: that neither of the Gemini models are not preview ones. Anthropic seems the best in this. Everything is in the API on day one. OpenAI te…

What is the state of using quants? For chat models, a few errors or lost intelligence may matter a little. But what is happening to tool calling in coding agents? Does it fail cata…

I am taking for SWE bench style problems where Todo doesn't help, except for more parallelism.

I run evals and the Todo tool doesn't help most of the time. Usually models on high thinking would maintain Todo/state in their thinking tokens. What Todo helps is for cases like A…

I work a lot on testing also SWE bench verified. This benchmark in my opinion now is good to catch if you got some regression on the agent side. However, going above 75%, it is lik…

Anybody knows if one can find an inference provider that offers input token caching? It should be almost required for agentic use - first speed, but also almost all conversations s…

I think that people are just too quick to assume this is amazing, before it is there. Which doesn't mean it won't get there. Somehow if I take the best models and agents, most hard…

I noticed a similar trends in selling on X. Put a claim, peg on some product A with good sales - Cursor, Claude, Gemini, etc. Then say, the best way to use A is with our best produ…

Yes. The article is click bait. With such a title I would have expected majority of the area to be dummy, but it is just structurally more silicon, exactly like a picture may be ma…

I used them both. I ended up disabling copilot. The reason is that the completions do not always integrate with the rest of the code, in particular with non-matching brackets. Ofte…

It seems recent years give us a lot of licenses (for core infra software) and now for LLMs. They all say in very legalese basically: these top 5-10 tech companies will not compete …

When I saw the name, I knew immediately this is Jyrki's work.

Exactly. The whole thing reads like some propaganda. It pits interesting topics ahead then to move on and push some agenda that sounds super political to me. Yes, some languages ar…

I think this is simply the default of lm-evaluation-harness. They said they ran every single benchmark they could out of the box.

The product they often presented as started in 20% time is Google news. I don't know the actual details, just this is what I remember from my time at Google (2006-2012).

It is true that nobody competes in the low power high efficiency workstation market or maybe such a market does not exist yet and Apple is creating it. But also as users, some were…