Can we please stop submitting fully AI-generated text to HN?
at least 50% of the front page would disappear if this were enforced
Don’t threaten me with a good time
Micro-Agent: Beat Frontier Models with Collaboration Inside Model API
11–20 of 26 posts
Re: Micro-Agent: Beat Frontier Models with Collaboration Inside Model API
#12Every one has been saying it’s all about the harness. This is an obvious result of that.
I think an optimal solution would be to have more seamless integration between harness and router roles. As each are only half the picture
Re: Micro-Agent: Beat Frontier Models with Collaboration Inside Model API
#13Re: Micro-Agent: Beat Frontier Models with Collaboration Inside Model API
#14I thought all model providers are doing this under the hood anyway in their UI?
They certainly seem to when A/B testing different models, and Fable routes to Opus 4.8 when guardrails fail.
Also, openrouter recently released a fusion router - https://openrouter.ai/blog/announcements/fusion-beats-fronti...
Re: Micro-Agent: Beat Frontier Models with Collaboration Inside Model API
#15> The phrase "frontier model" is starting to mean two things. One is a checkpoint. The other is a system boundary. LLM-isms aside, I don't think we want this to be the case? An LLM, for all its complexity, is something that can be reasoned about. It's picking the next token, until it hits an EOS. The semantics imposed on those tokens (reasoning ,tool call, etc.) are up to the user('s harness) to decide and act on. Th…
This seems to be a new trend. Noticed it with GPT "ultra" in their announcement[1]. I'm with you, a large language model and a system of many language models working together are not the same thing
Re: Micro-Agent: Beat Frontier Models with Collaboration Inside Model API
#16Looks nice (slop article aside), but why is VSR Hybrid only benchmarked on Humanity’s Last Exam and not the other two benchmarks (LiveCodeBench and GPQA-Diamond)? Is this an oversight or are the results too terrible to show?
Re: Micro-Agent: Beat Frontier Models with Collaboration Inside Model API
#17> The phrase "frontier model" is starting to mean two things. One is a checkpoint. The other is a system boundary. LLM-isms aside, I don't think we want this to be the case? An LLM, for all its complexity, is something that can be reasoned about. It's picking the next token, until it hits an EOS. The semantics imposed on those tokens (reasoning ,tool call, etc.) are up to the user('s harness) to decide and act on. Th…
They're applying misdirection so that we use their secret-sauce agentic framework, but like a black box and without seeing any of the internal reasoning patterns, cause that would give it away.
That's a deal-breaker for me. I need as much observability and control over my development workflow as possible; that's part of my secret sauce.
Re: Micro-Agent: Beat Frontier Models with Collaboration Inside Model API
#18sakana fugu landed sooo loudly ... I canceled my test subscription in two days.
Re: Micro-Agent: Beat Frontier Models with Collaboration Inside Model API
#19A sign of system-level optimization starting to overshadow raw/brute-force scaling of foundational models. My view is that foundational models are indeed statistic parrots, just like humans (humans are worse parrots, but human brain's context window is so small that they often do not recognize how broken was human-intermediated intelligence swarm, but such small context window might be a fundamental feature of so-called intelligence).
LLMs to me are better intelligence than humans in 3 aspects: 1. LLMs can somehow entirely do perspective taking, humans cannot even think self in next 10 minutes after making a decision 2. LLMs can somehow be asked to arbitrarily elevate and lower abstraction level (can be seen as a special form of perspective taking) 3. LLMs "think" instantly
All these innate capabilities should be combined with system level optimization to achieve the last 10% to be beyond human intelligence.
Re: Micro-Agent: Beat Frontier Models with Collaboration Inside Model API
#20This sounds like adding way too much complexity for something that will likely be covered fully by the next gen of frontier models within a single prompt. It also makes it all opaque and difficult to trace.