Jev returns probabilities instead of text, at $0.042 per million input tokens. Why that fits my ticket triage bot better than a chat model, and…
A new paper says LLMs catch 60% of JavaScript vulnerabilities and SAST catches zero. The zero is rigged. The per-CWE table underneath is what I'd…
A Columbia paper found LLMs edit already-optimal code 100% of the time. One prompt line halves it with zero false refusals. I reproduced it and…
Context compaction quietly drops the rules you give a coding agent. Two papers put numbers on it (17% and 53% retention). Here's what I moved…
A Purdue study got Qwen, Mistral and Llama to 'verify' a fake developer with a quiz they wrote themselves. What that means for your agent's…
IBM's consistency gap paper shows an agent passing 77% of runs succeeds five times in a row only 53% of the time. Here's the five-run…
A Stanford paper finds API benchmark scores run 3.4 points higher than the same models in their chat apps. What that means for how I…
Hugging Face lifted a 350M model's structured-output score with 100 GRPO steps and no labels. The trick isn't the model, it's three reward functions you…
A 4-bit model just beat the 16-bit checkpoint it was quantized from. I break down quantization-aware healing, the numbers, and what it changes for local…
Sentence Transformers v6 makes ColBERT-style retrieval trainable on one consumer GPU. The numbers, two traps in the fine print, and when it beats dense embeddings.