Edition of Thursday 19 November 2026

A 149M model handles 70% of phone-agent steps locally, Claude the rest

Comments on “A 149M model handles 70% of phone-agent steps locally, Claude the rest”

3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked

A solo developer, Chaitanya Talapalli, released a preprint and open code for Milo Pointer, a 149M-parameter text model that handles about 70% of phone-agent steps on the device and passes the rest to Claude.

Read the original at github.com. The judges saw only its text, with the site, the author and link domains removed; they are shown again after ranking.

Why it ranked

No. 45 of 144 with a score of 0.66. The panel rated it highest on new information (0.92) and substantiated (0.89), lowest on significance (0.56). Placed No. 45, No. 32 by score alone: the eleventh AI & machine learning story of the day (−0.080). The placement terms move stories; they are not part of the score.

AI judgeJudge 2claude-haiku-5-5
Strong technical paper on small-model routing for phone agents with pre-registration and reproducible code; gains are modest and narrow, and the audience is mainly AI-focused builders.
AI judgeJudge 3gpt-5.6-luna
Strongly substantiated original research with preregistration, code, released weights, reproducibility scripts, cost and latency measurements. It offers actionable evidence for efficient phone agents, though offline benchmark limits reduce significance and breadth.

Each judge wrote its line after answering the rubric, with the site and the author still hidden. Every answer behind this is in the table under Score.

Score

0.66total under rubric v2.3

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.56
  • Reader interest0.75
  • Audience breadth0.57
  • Practical relevance0.73
  • Substantiated0.89
  • Technical depth0.88
  • New information0.92
  • Counts against: Promotional0.07
  • Counts against: Overclaim0.26

Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).

QuestionJudge 1Judge 2Judge 3MeanSpreadWeightContribution (weight times mean)
SignificanceHow much does this change what people in tech know or can do?0.550.450.680.560.23+0.24+0.134
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.640.700.900.750.26+0.26+0.194
Audience breadthHow many people who build technology does it concern?0.580.500.620.570.12+0.13+0.074
Practical relevanceHow useful is it to someone who builds software or tech products?0.740.600.860.730.26+0.22+0.162
SubstantiatedHow well is it backed? Consider whether it is the primary source, and whether its main claims come with data, code, a demo, a reproducible method or citations.0.990.720.960.890.27+0.05+0.045
Technical depthHow technically substantive is it?0.970.780.900.880.19+0.05+0.044
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.880.900.980.920.10+0.05+0.046
PromotionalIs it mainly marketing with little substance (a press release, ad or sponsored post with no real information)? A launch post that carries real news is not promotional.0.060.120.030.070.09−0.19−0.013
OverclaimDo the headline or conclusions claim more than the body supports?0.350.300.120.260.23−0.11−0.028
Sum of contributions+0.657
Claim-check penalty0.000
Total, as published0.657

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.

The badge for this ranking, for the author's page or anyone's: one line of HTML, and it links back here.

Ranked #45 on Rubric, 19 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-19/45/"><img src="https://rubric.hrih.si/badge/2026-11-19/45.svg" alt="Ranked #45 on Rubric, 19 Nov 2026" width="245" height="28"></a>

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 1 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 19 Nov 2026, 05:47 UTC. It played no part in the ranking.

Panel for this edition

Four AI agents ranked this edition: three judges scored every story blind to its site and author, and a fourth compared the top stories’ claims with the sources they cite. Summaries are written by AI.

Model versions are pinned for every edition. How ranking works describes rubric v2.3.

Comments

Readers’ comments on this story have a page of their own, ranked by a public rubric rather than by votes.

Comments on “A 149M model handles 70% of phone-agent steps locally, Claude the rest”

More on Rubric

From the last 7 editions, chosen by shared topic, score and date.