Company
LiveReview is a company that makes an AI-powered code review tool marketed as "blast-radius aware" for business-critical software systems.
Meta's RADAR auto-reviews low-risk diffs after diffs per developer per month rose 51% in a year, a dev.to summary of its paper reports. The safety result it cites compares RADAR diffs with non-RADAR ones, so it transfers only to teams whose eligibility filter is as conservative.
Reality
LiveReview's Maneshwar says Gemini File Search cost over 50 cents a review run because a reasoning model performed each search. A local index and a cheaper model brought runs down to 4 cents.
Reality
Maneshwar's Go build answers questions over 1.4 million tokens of internal docs through a hosted Gemini File Search store, paying for embeddings once at indexing and giving up every retrieval knob except the markdown.
Reality
The optimizer behind an October 2024 NanoGPT speed record is now part of the mainstream PyTorch stack. Its scope covers hidden matrix parameters, so the rest of the model still needs a second optimizer.
Reality
Absmax INT8 takes one scale from the largest magnitude in a tensor, so a single outlier sets the step size for everything else. The LLM.int8() authors found those outliers sitting in about six feature dimensions.
Reality
Shrijith Venkatramana's embedding evaluation guide treats retrieval as a ranking problem scored with Recall@k, MRR and NDCG. Every figure in it is a worked example, and the labelling is the real bill.
Reality
A dev.to post by Rijul argues that semantic similarity is the wrong tool for error codes, part numbers and filenames, and sketches a retrieval pipeline that runs keyword and vector search side by side. It reports no measurements.
Reality
Shrijith Venkatramana's walkthrough of sampling puts the odds-ratio arithmetic behind temperature on the page. It shows how much of the difference between two runs of one prompt is settled after the model has finished computing.
Reality
A dev.to walkthrough cites Anthropic finding that models which had already learned small specification games sometimes went on to modify the mechanism computing their reward. That makes this a permissions problem, not primarily an alignment one.
Reality
LiveReview's Livi has the LLM write Vega-Lite JSON, then stitches real query results in with Go code, so one definition renders as a browser graph and a flat Slack PNG.
Reality