blog, website: edit out the AI writing tells readers called out on HN - #11324
Merged
Conversation
The HN thread on this post (item 49125065) spent most of its comments on the
writing rather than the engines. Readers quoted specific lines back as tells.
This is the same post with the same numbers, edited against the updated
no-ai-slop skill.
Every figure, table and link is unchanged, except that "27% of the memory"
is now the underlying 363 MB against 1328 MB from the table.
Two substantive framing fixes, both from the reply draft in
hn-reply-engines-post.md:
- vllm.cpp is no longer implied to be a speed win. The table is a tie, the
result is the install size, and the post now says so before a reader has to
work it out and post about it.
- Added one line on the language mix. Readers took the C++/Python/Go tree as
incoherence rather than as a Go core with per-ecosystem backends.
Cut throughout: the ledger metaphor ("what those ports buy", "not paid for in
throughput"), unearned framing ("the honest reading is", "has nothing to do
with"), the shape summary ("that is the general shape of these wins"),
confident deference ("people who are better at those models than we are"),
self-grading numbers ("a good result for a 66 MiB binary"), verbless
comparisons, three of the four exactness idioms, and the aphoristic headings
and verdicts. The double-tricolon summary is one plain clause now.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
One-by-one pass over the other four posts and the site templates, with the
same rules used on the engines post. All figures, tables, links and PR
numbers are unchanged everywhere; the edits are to prose only.
apex-moe-quantization: ledger metaphors were the main issue, eight uses of
buy/cost/pay/spend for things that are not money. Also "the honest reading
is", "that is the comparison that matters", and two section-ending aphorisms
("Size is a speed knob as much as a memory knob", "Q6_K is the ceiling worth
paying for").
localai-since-march-2023: light touch, this one already reads like a person.
Removed "the curve is not the point", a "not the feature list, but the four
decisions" contrast, and two "X is what made / is the piece that" forms.
parakeet-cpp-asr-on-cpu: six exactness idioms across one post, "byte for
byte" twice, "character for character" twice, "byte-identical" twice and
"bit-identical" once, including in the title. Down to one, kept where the
precision is load-bearing. Also the "what end-of-utterance detection buys
you" heading and the "we say so rather than averaging it away" flex.
what-landed-in-localai-4-8: no changes. It is dense, flat and ends every
section on a PR number or a plain fact, which is the shape the other posts
should look like.
Site templates: "Most backends wrap somebody else's engine. These do not."
was the same contrast the engines post opened with. Also "Not a degraded mode
that technically runs", "A port only ships once it matches the original",
"Speed is the part we then go and win ... not a marketing run", and the last
"byte for byte" on the landing page.
Hugo builds clean.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Three places said nineteen: the /engines/ page description, the JUL 2026 timeline entry on the landing page, and the header comment in data/engines.yaml. Eighteen is right, confirmed two ways. The "Backends built by us" table in the README has exactly 18 rows, and data/engines.yaml has 19 entries of which one is apex-quant, which is a quantization recipe rather than an engine. The two lists otherwise match name for name. The yaml comment is the likely origin: it read "the nineteen native engines the LocalAI team wrote, and the one quantization recipe that feeds them", which counts apex-quant twice. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This was referenced Aug 3, 2026
localai-bot
added
the
kind/documentation
mudler
added a commit
that referenced
this pull request
Aug 4, 2026
) * docs(blog): final figures for the 4.8 post, and the MLX provider The cycle closed at 374 PRs over twenty-one days, not the 321 over eighteen the post was written against. Corrects the summary, the opening line, the contributor count and the gallery total, and moves the date to the day the release is cut. Adds the MLX GEMM provider (#11137), which merged after the post was written and is the one number an Apple Silicon reader wants: 1.54x to 2.19x on an M4 with time to first token roughly halving, both arms toggled on one binary. The +/-10% caveat travels with the table rather than being left in the PR. Two lines edited against the no-ai-slop skill while I was in the file, the same pass #11324 ran over the engines post: - The opener balanced two clauses across a colon and closed on "without lying to you", which is the built-to-be-quoted shape readers picked out of the HN thread. It is a flat statement now. - "This is a new modality rather than a new backend under an existing one" is a binary contrast that says nothing the next clause does not. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5 [Read] [Edit] [Bash] * docs(blog): call vllm.cpp alpha, and finish the no-ai-slop pass vllm.cpp is not a released backend and the post read like it was. The old wording buried the caveat in a block quote at the end of the section and still said "first release of a young engine". It now says plainly, before the caveat can be skipped, that these are alpha development builds, that shipping them in 4.8 is about letting people try the thing rather than recommending it, and that llama-cpp stays the default. Also completes the no-ai-slop pass I had only half run. Counting the lines built to be quoted, headings and section endings included, the post is in reasonable shape: long flat informational stretches, tables followed by a plain finding, headings that are labels rather than epigram-verdicts. Three patterns survived, each one an item in eval.md: - "and inverts that:" set the usual shape against ours across a colon. The sentence works without the frame. - "Two things were conflated there: a signal, which needs one line, and the detail, which needs somewhere to put it" is a role-assignment pair. Says what happens instead. - "The maturity statement from the release notes is worth repeating in full" is throat-clearing in front of a quote, and the quote is gone. Left the rest alone. Minimum effective edit, not a rewrite. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5 [Read] [Edit] [Bash] * docs(blog): present vllm.cpp as a community project, with its own numbers The post described vllm.cpp as "a from-scratch port of vLLM, written and maintained by the LocalAI team". Two things wrong with that. It is a community project, and it has stopped being only a port: it loads GGUF, runs on CPU, Metal and Vulkan, ships speculative decoding and KV offload, and its benchmark page measures against llama.cpp, MLX-LM and DwarfStar as well as vLLM, because those are the engines it competes with on that hardware. vLLM's role is now stated for what it is, the reference implementation. Correctness is checked against it and the scoreboard is kept against it. Also flags that the name will probably change, since it is drifting far enough that vllm.cpp will eventually mislead. Adds real numbers from the project's own docs/BENCHMARKS.md rather than adjectives: 1.045x vLLM at concurrency 1 on Qwen3.6-27B NVFP4 with token-for-token identical output, 1.010x and 1.013x at c16 and c32 on the 35B MoE and behind below that, prefill 1.18x over llama.cpp on CPU aarch64, 97.6% of MLX-LM warm total on an M4. Upstream's own caution travels with them: it treats c2 through c32 as ties because its noise band is 0.5% and those margins are 0.7% to 1.7%. Every figure was checked against ~/_git/vllm.cpp/docs/BENCHMARKS.md rather than restated from memory. The heading is marked alpha to match the section body. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5 [Read] [Edit] [Bash] * docs(blog): say who maintains vllm.cpp, and add the DeepSeek Flash result Two corrections to the previous commit. "A community project" says nothing and was not quite true either. The LocalAI team maintains vllm.cpp. Community-first is the intent, not a description, so it now says that and says what backs it: its own repository, its own docs, benchmark record and issue tracker, and it runs without LocalAI anywhere in the picture. Adds the DeepSeek-V4-Flash result, which makes the divergence point better than any of the prose around it. That model does not run on vLLM on a single GB10: every vLLM-loadable checkpoint is 156 GB or more against a 119 GiB unified pool, and the only quant that fits is an extreme-low-bit GGUF that vLLM cannot load. vllm.cpp reads GGUF and runs it at 16.28 tok/s against ds4's 16.33, a parity result. Also notes MTP speculative decoding, token-identical to vLLM's and about 4% faster at concurrency 1. Both figures checked against ~/_git/vllm.cpp/docs/BENCHMARKS.md. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5 [Read] [Edit] [Bash] * docs(blog): lead the DeepSeek result with what we run, not with what vLLM cannot The previous version opened on "that model does not run on vLLM on a single GB10 at all". Wrong emphasis twice over: it makes a strong negative claim about another project the headline, and it buries the actual result, which is that vllm.cpp runs DeepSeek-V4-Flash at roughly 2-bit (IQ2_XXS mixed, about 80 GB) on a single DGX Spark and decodes at 16.28 tok/s against DwarfStar's 16.33. The size constraint is still there, stated as the reason the quant is what it is rather than as a point about vLLM: at 300B+ total parameters even a 4-bit checkpoint is 156 GB or more, so a 2-bit GGUF is what fits the Spark's 119 GiB unified pool. The table row now names the quant and the box (IQ2_XXS, one DGX Spark) instead of just "GGUF, GB10", since that is the part a reader with a Spark wants. Figures unchanged and still from ~/_git/vllm.cpp/docs/BENCHMARKS.md. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5 [Read] [Edit] [Bash] * docs(blog): say the new name is undecided "The name will probably change at some point" invited the obvious question. It now says the rename is expected and the name is still to be decided, which is the actual state. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5 [Read] [Edit] [Bash] --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The HN thread on Why we write our own C and C++ inference engines spent most of its 44 comments on the writing rather than the engines. Readers quoted individual sentences back as evidence. The strongest summary of the complaint came from one commenter:
This edits the personality out. Same posts, same claims, same numbers.
Guarantees
master.27% of the memorybecame the underlying363 MB against 1328 MBstraight from its own table, because the rule against verbless comparisons wanted a verb.hugobuilds clean.Per file
why-we-write-our-own-engines.md— the post that got hit. Two substantive framing fixes beyond the prose:bastawhizwas right that a handful of tok/s is not a result; the post now says "Those are ties" and puts the actual finding first, which is the install dropping from 9.1 GiB to 66 MiB at unchanged throughput.bwfan123read the C++/Python/Go tree as incoherence rather than a Go core with per-ecosystem backends.Cut: the ledger metaphor (
what those ports buy,not paid for in throughput),the honest reading is,has nothing to do with,that is the general shape of these wins,people who are better at those models than we are,a good result for a 66 MiB binary, the verbless comparisons, and the aphoristic headings (Parity is the gate, speed is the follow-up→The two where we are slower). Quotable-line count went from ~20 to 3, and the ones left are concessions rather than boasts.apex-moe-quantization.md— eight uses of buy/cost/pay/spend for things that are not money. Plusthe honest reading is,that is the comparison that matters, and two section-ending aphorisms.localai-since-march-2023.md— light touch; this one already reads like a person wrote it. Six small fixes.parakeet-cpp-asr-on-cpu.md— six exactness idioms in one post (byte for byte×2,character for character×2,byte-identical×2,bit-identical), including in the title. Down to one, kept where the precision is load-bearing.what-landed-in-localai-4-8.md— no changes. Dense, flat, every section ending on a PR number or a plain fact. It is the model the others should follow.Site templates —
Most backends wrap somebody else's engine. These do not.was the same contrast the engines post opened with. AlsoNot a degraded mode that technically runs,A port only ships once it matches the original,Speed is the part we then go and win ... not a marketing run, and the lastbyte for byteon the landing page.Engine count fixed
Three places said nineteen: the /engines/ page description, the JUL 2026 timeline entry on the landing page, and the header comment in
data/engines.yaml. Eighteen is right, confirmed two ways:README.mdhas exactly 18 rows.data/engines.yamlhas 19 entries, one of which isapex-quant, a quantization recipe rather than an engine. The two lists otherwise match name for name.The yaml header comment is the likely origin. It read the nineteen native engines the LocalAI team wrote, and the one quantization recipe that feeds them, which counts
apex-quanttwice.One thing left for you
The animated background. Two commenters never reached the argument. One said outright that laggy scrolling is why he only read the first few screens, another that it spun up his CPU fan. That cost more readers than any sentence in the post, and it is out of scope here.